Skip to content

MCP servers › com.writerslogic.agents › writerslogic-agents

MCP server · registry snapshot 2026-11-16 · last tested 2026-11-16

writerslogic-agents MCP server

Registry name com.writerslogic.agents/writerslogic-agents

WritersLogic verifiable AI agents — the publisher's title

by agents.writerslogic.com · domain (the registry's namespace rule)source link does not open (missing or private)Website ↗

262 deterministic, x402-paid agents for audit, research, patents, and dev review. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-11-16version 1.0.0streamable HTTP262 tools

Summary

com.writerslogic.agents/writerslogic-agents is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain agents.writerslogic.com. Its linked repository, github.com/writerslogic/ai-agents, does not open publicly (missing or private). On 2026-11-16 ProtocolProbe connected to it in read-only mode and read its inventory: 262 tools, 0 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Repository
link does not open publicly
Tools
262
Last tested
2026-11-16

Tool list size

205,229 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (262 tools). Counted with Anthropic's token counter on 2026-11-16, from the tool list we read on 2026-11-16. Median across 28,560 counted servers: 2,657 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-16 (agents.writerslogic.com), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.0.0).

Add to your client

Observed fact

This server accepted a session without any credential and lists 6 tools whose name or declaration suggests they change data (patch-anchor, edit-anchor-check, update-dialect, json-patch-conflict, chess-move and 1 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-16.

Worth knowing before you connect it

  • The linked repository does not open publicly, so the code cannot be reviewed through it.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-16
Mode
read-only (no tool calls)
Latest version
1.0.0, published 2026-11-15 (registry, as of the 2026-11-16 snapshot)
First listed version
2026-11-15 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-11-16
Package and repository
checked 2026-11-16
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

1 found in the records we hold

  • The repository link does not open: GitHub answered HTTP 404 (it does not exist, or it is private). — api.github.com · 2026-11-16 · all servers with this fact

Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-11-15, listed on 2026-11-16 with version 1.0.0 (published 2026-11-15).

Source: the official MCP Registry list on 2026-11-15 and on 2026-11-16.

What it is

What does this server offer?

Observed inventory
262tools
0resources
0prompts

None of its 262 tools are described as changing anything. For 262 the reading was uncertain, so no mark is shown.

  • lead-enrichmenton 1 other server

    “Autonomous Lead Enrichment — Scrapes a company homepage, deduces its value proposition and buyer persona, and drafts a targeted B2B cold email.”

    2 inputs, 1 required
    • urlstringrequired“Company homepage URL; https:// is assumed if omitted.”
    • senderContextstring“What you sell, used to tailor the pitch.”
  • contract-auditoron 1 other server

    “Smart Contract Auditor — Source-level security review of Solidity: pass/warn/fail verdict, 0-100 risk score, severity-ranked findings with exact file:line, exploit scenario and a fix, plus a SARIF 2.…”

    5 inputs
    • codestring“Raw Solidity source (one or more files concatenated).”
    • contractNamestring“Contract to focus on when several are present.”
    • filesarray“Alternative to code: Solidity files with repository-relative paths.”
    • addressstring“Alternative to code: an on-chain contract address.”
    • chainIdinteger“EVM chain id for address; default 1 (Ethereum mainnet).”
  • market-predictoron 1 other server

    “Prediction Market Analyzer — Independent probability that a Polymarket or Kalshi market resolves Yes, checked against the live book.”

    7 inputs
    • textstring“News excerpt or event description.”
    • questionstring“Exact market question; inferred when omitted (read from the market when market is given).”
    • marketstring“Polymarket slug, market URL or conditionId, or a Kalshi ticker or URL.”
    • minEdgePctnumber“Minimum edge after taker fees, in percentage points, before verdict.action is BUY_YES or BUY_NO (default 5).”
    • bankrollUsdnumber“Converts the quarter-Kelly fraction into verdict.size_usd.”
    • marketPriceYesnumber“Current implied Yes probability, used to compute edge.”
    • marketPriceScalestring“Force the unit of marketPriceYes: percent (35 = 35%) or fraction (0.35 = 35%).”
  • arbitrage-lawyeron 1 other server

    “Cross-Platform Arbitrage & Resolution Rules Lawyer — Finds fine-print divergences between two prediction markets (e.g.”

    5 inputs, 2 required
    • marketAobjectrequired
    • marketBobjectrequired
    • minEdgeBpsnumber“Default 100 (1%).”
    • bankrollUsdnumber“Used to convert the Kelly fraction to USD.”
    • minAnnualizedReturnPctnumber“Minimum annualized risk-adjusted return, in percent, for verdict.action ARBITRAGE_SAFE (default 5).”
  • heal-scraperon 1 other server

    “Self-Healing Scraper & DOM-to-JSON Compiler — Synthesizes durable CSS selectors (Cheerio; no XPath) for a target JSON schema, proves them against the live DOM in-request, and returns the extracted da…”

    4 inputs, 1 required
    • urlstring“Page to fetch.”
    • htmlstring“Raw HTML to use instead of fetching.”
    • targetSchemaobjectrequired“JSON Schema of the fields to extract: an object whose properties are string/number/integer/boolean (or arrays of those), or an array whose items are such an ob…”
    • previousBrokenSelectorsobject“Map of field name to the CSS selector that stopped working.”
  • token-trap-detectoron 1 other server

    “On-Chain Bytecode & Unverified Token Trap Detector — Reads live Base bytecode, proxy slots (EIP-1967/beacon/zeppelinos/EIP-1822/EIP-1167), ERC-20 state, and privileged selectors to score honeypot and…”

    2 inputs, 1 required
    • tokenAddressstringrequired“Token contract address on Base.”
    • sourceCodestring“Optional Solidity source claimed for the token.”
  • competitor-battlecardon 1 other server

    “SaaS Pricing & Competitor Battlecard Spy — Reads up to 3 competitor sites (homepage and pricing page, fetched in parallel) and returns a deal battlecard in under a minute: a verdict headline with con…”

    3 inputs, 2 required
    • ourProductDescriptionstringrequired
    • competitorUrlsarrayrequired“Competitor homepage or pricing URLs.”
    • scenarioobject“Optional deal size used to compute monthly and annual cost per verified tier: seats for per-seat prices, monthlyVolume for usage prices.”
  • diff-gatekeeperon 1 other server

    “PR / Dependency Breaking-Change & Exploit Gatekeeper — Merge gate for a pull request: pass/warn/fail verdict, 0-100 risk score, the top findings with file:line and a fix, drop-in patches, GitHub Chec…”

    5 inputs
    • gitDiffstring“Raw unified diff (git diff output).”
    • prUrlstring“Alternative to gitDiff: a public GitHub pull request, commit or compare URL (github.com/owner/repo/pull/123).”
    • filesarray“Alternative to gitDiff: changed files with their patch hunks, as returned by GitHub's pull request files API.”
    • packageJsonDiffstring
    • contextstring“What the PR is supposed to do.”
  • medical-bill-auditoron 1 other server

    “Medical Bill Upcoding & Overcharge Slasher — Paste an itemized hospital or physician bill and get a decision first: dispute it or not, the estimated dollars above a defensible price, and a dispute le…”

    12 inputs, 1 required
    • billTextstring“Alternative to lineItems: paste the itemized bill, one line item per line, e.g.”
    • lineItemsarray
    • facilityTypestringrequired
    • coveragestring“Determines which No Surprises Act protections can apply.”
    • patientStatestring
    • visitSummarystring“What actually happened: symptoms, duration, tests, treatment.”
    • facilityNamestring
    • patientNamestring
    • accountNumberstring
    • goodFaithEstimateAmountnumber“Good Faith Estimate received (self-pay).”
    • claimTypestring“Physician (CMS-1500) or hospital/facility (UB-04) bill.”
    • billReceivedDatestring“Date the initial bill was received; used for the 120-day dispute deadline.”
  • chargeback-fighteron 1 other server

    “E-Commerce Chargeback Representment Builder — Tells a merchant whether to fight or accept a card dispute: scores win probability against the network rubric for the reason code (Visa, Mastercard, Amex…”

    7 inputs, 4 required
    • networkstringrequired
    • reasonCodestringrequired“e.g.”
    • disputeDatestring
    • disputeFeeUsdnumber“Fee your processor charges to contest the dispute and does not return on a loss; used to net the expected value.”
    • responseDeadlinestring“Deadline shown in your processor's dispute dashboard (YYYY-MM-DD); days remaining are computed from it.”
    • orderDetailsobjectrequired
    • evidenceobjectrequired
  • contract-terminatoron 1 other server

    “Dark Pattern Contract & Subscription Exit Lawyer — Paste a contract or Terms URL and get the decision first: send notice by a computed date, or the window has passed.”

    13 inputs, 3 required
    • termsUrlstring“Terms of Service or cancellation policy URL.”
    • contractTextstring
    • vendorNamestringrequired
    • userJurisdictionstringrequired“e.g.”
    • reasonForExitstringrequired
    • customerTypestring
    • customerNamestring
    • accountIdentifierstring
    • contractStartDatestring
    • signupMethodstring
    • monthlyFeenumber“What you pay per month, USD.”
    • annualFeenumber“What you pay per year, USD, if billed annually.”
    • earlyTerminationFeeUsdnumber“Early-termination fee the vendor says you owe, USD, if any.”
  • tariff-engineeron 1 other server

    “Global Customs & Tariff Engineering Optimizer — Classifies a product under the HTS with GRI reasoning and verifies the code and general (MFN) rate against the live USITC schedule, flags when a specif…”

    10 inputs, 5 required
    • productNamestringrequired
    • materialsBreakdownarrayrequired
    • intendedUsestringrequired
    • originCountrystringrequired
    • destinationCountrystringrequired
    • productDescriptionstring“Construction, dimensions, how it works, packaging.”
    • customsValueUsdnumber“Entered value, used to estimate duty and savings.”
    • currentHtsCodestring
    • importStateOfAssemblystring
    • productUrlstring“Public product or spec-sheet page.”
Show 88 more tools
  • patent-design-aroundon 1 other server

    “Patent Design-Around & Freedom-to-Operate Architect — Paste patent claims or give a patent number.”

    6 inputs, 1 required
    • patentClaimsTextstring“Numbered claims (at least the independent claims).”
    • proposedProductDescriptionstringrequired
    • patentNumberstring“Publication number such as US7629993B2.”
    • jurisdictionstring“Defaults to US.”
    • annualRevenueUsdnumber“Annual revenue that depends on the product; sizes the dollar exposure in the headline.”
    • assumedRoyaltyPctnumber“Assumed running royalty as a percent of revenue, for the exposure illustration.”
  • accessibility-patcheron 1 other server

    “ADA / WCAG Lawsuit Shield & DOM Auto-Patcher — Returns a FAIL / REVIEW / PASS verdict for a page's HTML (pasted or fetched from a URL) against the WCAG failures most cited in ADA demand letters: alt …”

    2 inputs
    • urlstring“Page to audit.”
    • htmlstring
  • clarification-impacton 1 other server

    “Prediction-Market Clarification Impact Pricer — Prices a prediction-market rules clarification as a trade.”

    11 inputs, 1 required
    • marketstringrequired“Polymarket market slug, polymarket.com URL or conditionId; or a Kalshi market ticker (rules from the public trade-api v2).”
    • rulesBeforestring“Rules text before the change.”
    • clarificationTextstring“The clarification / Additional context text.”
    • positionobject
    • bankrollUsdnumber“Used to turn the Kelly fraction into dollars.”
    • sizeUsdnumber“Intended order size in USD (default 100).”
    • priorYesnumber“Override for the pre-clarification fair P(YES); default is the Polymarket CLOB price history just before the clarification, falling back to the current YES ord…”
    • feeRatenumber“Taker fee coefficient: fee = shares * feeRate * p * (1 - p).”
    • minEdgeBpsnumber“Minimum edge after fees and slippage, in bps of cost (default 100).”
    • minMoveBpsnumber“Fair-value move below which the answer is NO_MATERIAL_CHANGE (default 100).”
    • kellyFractionnumber“Fraction of full Kelly to stake (default 0.25).”
  • legal-cite-verifieron 1 other server

    “Legal citation and quotation verifier (US case law) — Extracts US reporter citations from a brief (U.S., S.”

    6 inputs
    • textstring“Brief or memo text.”
    • citationsarray“Citations to check instead of, or in addition to, text.”
    • quotesarray“Quotations to find verbatim in the cited opinion.”
    • check_propositionsboolean“Default false.”
    • propositionsarray
    • max_citationsinteger“Distinct reporter citations to check.”
  • milestone-verifieron 1 other server

    “Grant Milestone Verifier with Signed Release Attestation — Decides whether a grantee met a milestone before a DAO releases the next tranche or stream.”

    4 inputs, 2 required
    • milestoneobjectrequired
    • evidenceobjectrequired
    • payoutobject
    • releasePolicyobject
  • “UMA Dispute EV Desk — For a Polymarket market inside its roughly two-hour UMA challenge window, reads the live proposal on Polygon (adapter, optimistic oracle, bond, finalFee, expiry), judges P(propo…”

    6 inputs, 1 required
    • marketstringrequired“Polymarket slug, market/event URL, conditionId or questionID.”
    • proposalobject“Overrides for on-chain proposal fields (what-if or replay).”
    • positionobject“Your holding in this market.”
    • pricesobject“Current prices of the first and second listed outcomes, USD per share.”
    • evidenceUrlsarray“Public pages to treat as evidence.”
    • paramsobject
  • “DeFi Cover Claim Adjudicator — Predicts whether a DeFi cover claim (Nexus Mutual or any provider's wording) will be approved and for how much.”

    8 inputs, 3 required
    • wordingobjectrequired“The cover wording: a Nexus Mutual product (id or name), a URL (HTML or PDF), or pasted text.”
    • incidentobject
    • transactionsarray“Transactions in which the claimant lost (or deposited, or recovered) funds.”
    • claimantstringrequired“Address that suffered the loss (the Impacted Account).”
    • coverobjectrequired
    • deductibleobject“Overrides any deductible found in the wording.”
    • claimedLossobject“Loss the claimant asserts, in cover-asset units.”
    • claimDatestring“ISO 8601 date the claim is (to be) filed; default now.”
  • vault-exit-lawyeron 1 other server

    “Vault Exit Lawyer — Before moving treasury funds out of an ERC-4626 or ERC-7540 vault: reads the chain at one pinned block and returns how much can exit now, the haircut vs convertToAssets, partial-e…”

    5 inputs, 3 required
    • chainstringrequired“Chain the vault lives on.”
    • vaultstringrequired“ERC-4626 or ERC-7540 vault address.”
    • exitobjectrequired“Exactly one of shares or assets, as base-unit integer strings.”
    • holderstring“Address that holds the shares.”
    • docsUrlsarray“Public documentation pages whose redemption claims are checked against the contract.”
  • foreignResearchScouton 1 other server

    “Cross-Lingual Dark Science Arbitrage Scout — Finds scientific work that exists only in non-English literature.”

    7 inputs
    • researchTopicstring“English research topic, e.g.”
    • technicalBottleneckstring“English description of an unsolved technical bottleneck.”
    • seedPaperstring“An English-language paper you already know, as a DOI (bare or doi.org URL) or arXiv id/URL.”
    • targetLanguagesarray“ISO 639-1 codes of non-English languages to mine (max 6).”
    • fromDatestring“Earliest publication date.”
    • toDatestring“Latest publication date (inclusive).”
    • maxResultsinteger“Discoveries to return (default 5, max 8).”
  • arxiv-to-codeon 1 other server

    “arXiv-to-Production Code & Hyperparameter Compiler — Fetches an arXiv paper's full text (ar5iv), selects method, pseudocode, hyperparameter tables and ablations, and returns a core-algorithm summary,…”

    3 inputs, 1 required
    • arxivIdstring“arXiv id or URL, e.g.”
    • searchQuerystring“Title or keywords; the top arXiv hit is used.”
    • targetLanguagestringrequired
  • prior-art-invalidatoron 1 other server

    “Global Prior-Art Patent Invalidator — Screens a patent's claims against scholarly literature published before the priority date (arXiv, OpenAlex, Europe PMC, Crossref, HAL, J-STAGE; English, Chinese,…”

    3 inputs
    • patentClaimsTextstring“Claims to attack, numbered as in the patent (e.g.”
    • priorityDatestring“Earliest effective filing/priority date, YYYY-MM-DD.”
    • patentNumberstring“Publication number such as US7629993B2.”
  • replication-auditoron 1 other server

    “Scientific Consensus & Replication Failure Auditor — Give a DOI, arXiv id, PMID, URL, title or a free-text claim and get a verdict-first screen of whether the finding has been retracted, contradicted…”

    6 inputs
    • paperTitleOrDoistring“DOI (10.xxxx/..., bare or doi.org URL), arXiv or PubMed URL, or title of the paper to audit.”
    • doistring“DOI of the paper to audit (bare, doi: or doi.org URL).”
    • arxivIdstring“arXiv id or arxiv.org URL (2106.09685, arXiv:1706.03762, hep-th/9901001).”
    • pmidstring“PubMed id (digits) or pubmed.ncbi.nlm.nih.gov URL.”
    • urlstring“A doi.org, arxiv.org or pubmed.ncbi.nlm.nih.gov URL for the paper.”
    • scientificClaimstring“Free-text claim; the originating and closely related works are located by search.”
  • abandoned-compound-mineron 1 other server

    “Abandoned Compound & Uncommercialized Trial Miner — Finds shelved drug and biologic candidates worth a second look.”

    6 inputs
    • biologicalTargetOrConditionstring“Disease, condition or biological target (e.g.”
    • materialPropertystring“Desired material property (e.g.”
    • compoundstring“A compound you already have in mind, as a drug name or ChEMBL id (e.g.”
    • nctIdstring“A ClinicalTrials.gov trial id (e.g.”
    • includeCompletedNoFollowUpboolean“Include completed Phase 1/2 non-industry trials with no later industry Phase 2/3/4 trial of the same intervention.”
    • maxCandidatesinteger“Dossiers to produce (default 4, max 8).”
  • unicode-safety-gateon 1 other server

    “Adversarial Unicode & Trojan Source gatekeeper — Scans a public GitHub repo, a pull request, a unified diff or a list of files for adversarial Unicode with the 19 rules (USC001-USC019) of dcondrey/un…”

    8 inputs
    • filesarray“Files to scan in full.”
    • diffstring“Unified diff (git diff output).”
    • repostring“Alternative to files and diff: a public GitHub repository, owner/repo or https://github.com/owner/repo[/tree/ref].”
    • refstring“Branch, tag or commit for repo; defaults to the default branch.”
    • prUrlstring“Alternative to files and diff: a public GitHub pull request, commit or compare URL.”
    • identifierPolicystring“Default ascii-only: any non-ASCII identifier is flagged (USC019).”
    • permittedScriptsarray“Used with permitted-scripts.”
    • scanExcludedboolean“Also scan paths the upstream scanner skips (node_modules/, vendor/, dist/, build/, .lock, .min.js, images, archives).”
  • audit-prose-forensicson 1 other server

    “Forensic AI-trajectory & prose craft auditor — Deterministic prose forensics: word echoes within 50 words, repeated 3-6-grams, sentence-starter runs, hedge/filter/passive/nominalization density, burs…”

    3 inputs, 1 required
    • textstringrequired“Plain-text prose to audit (English).”
    • revisionHistoryarray“Earlier drafts of the same text with ISO-8601 timestamps; adds a revision trajectory as process evidence.”
    • genrestring“Context for the editorial pass only.”
  • compressibility-rankon 1 other server

    “Rank the most compressible (cliched) phrases in a chapter — Finds the phrases in a passage that compress most against a reference corpus of generic prose, so a writer can target the low-entropy spans…”

    7 inputs, 1 required
    • textstringrequired“The chapter or passage to score.”
    • modestring“sentence (default) scores at sentence boundaries; ngram scores every sliding window of ngramSize words.”
    • ngramSizeinteger“Words per window when mode is ngram (default 5).”
    • minCharsinteger“Minimum characters per candidate span (default 18).”
    • topNinteger“How many lowest-score spans to return (default 10).”
    • referencestring“Optional reference corpus to prepend before compression.”
    • useBuiltInReferenceboolean“Pass false to score with no reference corpus (local redundancy only).”
  • crosstalk-deliberateon 1 other server

    “Crosstalk epistemic swarm & falsification engine — Stress-tests a research question instead of answering it once.”

    4 inputs, 1 required
    • questionstringrequired“The question or claim to deliberate.”
    • contextstring“Optional background, constraints, data or prior attempts.”
    • maxHypothesesinteger“Independent hypotheses to generate and attack (default 3).”
    • papersarray“Up to 5 papers you already have, as arXiv ids or URLs (2201.11903, arxiv.org/abs/...) or DOIs (10.xxxx/..., doi.org URLs).”
  • audit-public-recordon 1 other server

    “OnRecord statutory clock & redaction auditor — Audits an agency's public-records response and leads with a decision (late, redaction problems, incomplete, pending or no violation found).”

    10 inputs, 3 required
    • jurisdictionstringrequired“OnRecord jurisdiction code.”
    • requestDatestringrequired“Date the agency received the request (YYYY-MM-DD or RFC 3339; read in the offset written).”
    • responseDatestring“Date of the agency's determination/response.”
    • asOfDatestring“Observation date when responseDate is omitted; defaults to today (UTC).”
    • extensionNoticesarray
    • documentsarrayrequired
    • agencyNamestring“Agency that received the request; fills the follow-up letter.”
    • requesterNamestring“Your name, for the follow-up letter signature.”
    • requestReferencestring“The agency's request or tracking number, for the follow-up letter.”
    • gapThresholdDaysinteger“Report gaps between dated events longer than this (default 30).”
  • “WARM verifiable agent memory — Persistent memory for AI agents as a pay-per-call API, no database to run.”

    11 inputs, 1 required
    • opstringrequired
    • tenantIdstring“Required for API-key callers (namespace as key:<tenantId>; keep it unguessable).”
    • factsarray
    • textstring“remember: free text; facts are extracted by a fast model and kept only if subject and object occur verbatim.”
    • sourcestring“remember: provenance label for facts extracted from text.”
    • querystring
    • patternobject“Exact (case- and whitespace-insensitive) match on any of subject, predicate, object.”
    • saidstring
    • asOfinteger or string“Epoch milliseconds or an ISO 8601 date/time (UTC when no offset).”
    • limitinteger
    • historystring“recall: only facts current at asOf (default) or every status.”
  • smt-contract-proveron 1 other server

    “SMT Contract & Policy Logic Prover — Answers a yes/no logic question about contract clauses, IAM/OPA policies or business rules with a solver-backed result and a plain-language headline and next step.”

    5 inputs
    • clausesarray“Natural-language contract clauses, IAM/OPA policy statements or business rules, each with a caller-chosen id.”
    • textstring“Alternative to clauses: the contract, policy or rules pasted as plain text.”
    • querystring“The question, e.g.”
    • irobject“Formal IR, solved with zero LLM calls: {variables:[{name,type:bool|int|real,min?,max?}], constraints:[{id,expr,source?}], query:{mode:possible|always|consisten…”
    • budgetobject“Optional lower step budgets.”
  • ai-bom-license-resolveron 1 other server

    “AI-BOM License Chain Resolver for Hugging Face Models — Walks the Hugging Face lineage of up to 10 models (base_model chain, training datasets; at most 30 nodes, 4 generations) and applies a curated,…”

    4 inputs, 2 required
    • modelsarrayrequired“Hugging Face model repo ids (owner/name) used together in the system.”
    • datasetsarray“Extra Hugging Face dataset repo ids; datasets named on the model cards are followed automatically.”
    • usesarrayrequired“Intended uses to decide, each evaluated independently.”
    • dataset_termsstring“advisory (default): a dataset license restriction yields UNDETERMINED because it is unsettled whether it binds trained weights.”
  • state-model-checkeron 1 other server

    “State Machine Model Checker — Returns PASS, FAIL or INCONCLUSIVE for a finite state machine, protocol, or concurrent routine, with the shortest failing path as readable process.transition steps and a…”

    5 inputs
    • specobject“Formal spec (zero LLM calls).”
    • descriptionstring“Natural-language workflow or protocol; translated to a spec by an LLM, with each transition quoted from the text.”
    • codestring“Source code of a state machine, protocol, or concurrent routine; translated to a spec by an LLM, with each transition carrying its verbatim source span.”
    • propertiesarray“Properties to check, in plain language (with description or code only).”
    • optionsobject
  • causalRefereeon 1 other server

    “Causal Claim Referee — Referees a causal claim against an observational table (JSON rows, CSV text, or a published contingency table with counts) and leads with a verdict, confidence, whether the cla…”

    19 inputs, 4 required
    • dataarray“Observational table as an array of row objects (at most 20000 rows).”
    • csvstring“Alternative to data: CSV text with a header line (comma, semicolon or tab separated; quoted fields allowed; at most 20000 data rows).”
    • countColumnstring“Name of a column holding how many times each row repeats, so a published contingency table can be sent as a few aggregate rows (counts must be non-negative int…”
    • treatmentstringrequired“Column with exactly two distinct values.”
    • outcomestringrequired“Binary column (risk difference, risk ratio, odds ratio) or numeric column (mean difference).”
    • covariatesarrayrequired“Candidate adjustment variables (at most 12).”
    • claimstringrequired“The causal claim being refereed, in plain language.”
    • dagobject“Your causal DAG (formal input: no LLM is called to build the graph or, by default, the report).”
    • treatedValuestring or number or boolean“Treatment value that counts as treated; required unless the values are numeric or boolean (then the larger is treated).”
    • successValuestring or number or boolean“Outcome value that counts as success for a binary outcome; same default rule.”
    • outcomeTypestring“Force the outcome type; inferred from the number of distinct values otherwise.”
    • claimDirectionstring“Direction of the claimed effect of treated vs control; default nonzero.”
    • binsinteger“Quantile bins for numeric covariates, default 4.”
    • alphanumber“Significance level for the permutation test and the (1-alpha) bootstrap interval, default 0.05.”
    • seedinteger“Seed for bootstrap and Monte Carlo; default derived from the input hash.”
    • bootstrapRepsinteger
    • permutationSamplesinteger“Used only when the exact enumeration would exceed 1000000 label assignments.”
    • llmReportboolean“Ask a model to write the executive report in prose (numbers verified in code, template fallback).”
    • descriptionsobject“Optional one-line description per variable, used only to propose the DAG.”
  • sequence-identifieron 1 other server

    “Integer Sequence Identifier — Identifies an integer sequence from terms (a JSON array or pasted text), an OEIS A-number, a safe-parsed formula or recurrence, or a description, and leads with a verdic…”

    9 inputs
    • termsarray“Integer terms, 4 to 60, each at most 40 digits.”
    • termsTextstring“Alternative to terms: the terms pasted as text, separated by commas, spaces or semicolons (for example copied from a spreadsheet, a paper or an OEIS data line).”
    • aNumberstring“Alternative to terms: an OEIS A-number (A000108) or oeis.org URL.”
    • formulastring“Alternative to terms: a closed form in n such as "binomial(2*n,n)/(n+1)", or a recurrence such as "a(n) = a(n-1) + a(n-2)" (with initialTerms).”
    • initialTermsarray“Seed values a(start), a(start+1), ...”
    • startinteger“Index n of the first expanded term; default 0.”
    • countinteger“How many terms to expand from the formula; default 20.”
    • descriptionstring“Alternative to terms and formula: a plain-language description.”
    • explainboolean“Ask a model for a one-sentence explanation drawn only from the matched OEIS entry; its quote is verified in code, otherwise the entry name is returned.”
  • future-work-mineron 1 other server

    “Open Research Opportunity Miner — Leads with a verdict (OPEN_GAPS_FOUND, NO_CLEAR_OPEN_GAPS or NO_GAPS_EXTRACTED), a confidence, a headline naming the top gap with its quoted evidence, and the next s…”

    7 inputs
    • querystring“Research topic, e.g.”
    • seedsarray“Seed papers you already have: arXiv ids or URLs (2106.09685, arXiv:1706.03762, arxiv.org/abs/...), DOIs or doi.org URLs, or PMIDs (PMID:12345678 or a PubMed UR…”
    • fromDatestring“Only topic-search papers published on or after this date (YYYY-MM-DD).”
    • toDatestring“Only topic-search papers published on or before this date (YYYY-MM-DD).”
    • maxPapersinteger“Papers to analyse, at most 25 (default 10); seeds count toward it.”
    • fieldstring“Field or discipline keyword added to the topic search, e.g.”
    • modestring“fast: zero model calls (lexical clustering and lexical addressed-check).”
  • reference-verifieron 1 other server

    “Bibliography Reference Verifier — Checks every reference in a bibliography against Crossref, OpenAlex, arXiv and Europe PMC and leads with a verdict (FIX_REQUIRED, REVIEW_RECOMMENDED, INCOMPLETE or A…”

    8 inputs
    • bibtexstring“BibTeX/BibLaTeX text (the contents of a .bib file).”
    • latexstring“LaTeX source with a thebibliography environment (\bibitem) or embedded filecontents .bib; \cite commands supply citation contexts and are checked against the e…”
    • referencesstring“Plain-text reference list (numbered, blank-line separated, or one per line; APA, IEEE, Vancouver, Chicago).”
    • arxivIdstring“arXiv id or URL; references are read from the ar5iv HTML (.ltx_bibitem), falling back to the PDF.”
    • pdfUrlstring“Public PDF URL.”
    • identifiersarray“Bare identifiers instead of a bibliography: up to 150 DOIs (bare, doi: or doi.org URL), arXiv ids or URLs, or PMIDs (bare, PMID: or PubMed URL), mixed freely.”
    • manuscriptstring“Optional manuscript text (LaTeX or plain) that supplies citation contexts: \cite keys, [n] numbers or Author (year) citations.”
    • checkSupportboolean“Needs manuscript text (or latex, arxivId, pdfUrl).”
  • dependency-advisoron 1 other server

    “Dependency Underuse & Replacement Advisor — Audits the dependencies of a public GitHub repo, commit or pull request (or uploaded manifests and sources) and returns a pass/warn/fail verdict, a 0-100 r…”

    6 inputs
    • repostring“Public GitHub repository: owner/repo, https://github.com/owner/repo[/tree/ref], a commit URL, or a pull request URL (analyzed at the PR head).”
    • refstring“Branch, tag or commit; defaults to the default branch.”
    • filesarray“Alternative to repo: manifests (package.json, lockfile, pyproject.toml, requirements.txt, Cargo.toml) and source files with repository-relative paths.”
    • ecosystemsarray“Restrict the analysis; default all detected.”
    • modestring“deterministic makes no model call; auto makes at most one, only for symbols the curated table cannot decide.”
    • repoLicensestring“SPDX id of the repository's license, for alternative ranking; detected from manifests or LICENSE when absent.”
  • paperContradictionson 1 other server

    “Paper Contradiction Finder — Takes 2 to 4 papers (DOI, arXiv id, PMID or their URLs) on a shared question and answers whether their reported numbers conflict: a verdict (CONTRADICTION_FOUND / NO_CONT…”

    3 inputs, 1 required
    • papersarrayrequired“2 to 4 papers on a shared question, each a DOI (bare, doi: or doi.org URL), an arXiv id or arxiv.org URL, or a PMID (bare, PMID:n, or a pubmed.ncbi.nlm.nih.gov…”
    • claimstring“Optional claim or question to focus on; claims about it are paired first.”
    • modestring“full (default): one model call judges whether candidate claim pairs measure the same quantity in comparable populations.”
  • reconcile-ledgeron 1 other server

    “Exact Ledger Reconciler — Explains which charges, refunds and fees make up a Stripe, PayPal or bank payout, with an exact solver instead of a model: subset-sum over integer minor units (meet-in-the-m…”

    13 inputs
    • itemsarray“Ledger lines.”
    • settlementsarray“Payouts or bank settlement totals to explain.”
    • feeSchedulesarray“Candidate fee schedules; the solver reports which one reconciles each settlement.”
    • withholdingsarray
    • fxRatesarray“Direct rates only (1 from = rate to).”
    • textobject“Messy source text for collections not given structurally.”
    • defaultCurrencystring“Currency for text rows that state none.”
    • crossCheckboolean“Run two independent LLM translations and keep only rows both produced (default true).”
    • conventionsobject“Restrict the conventions searched (default: all rounding modes x both scopes x both FX date policies).”
    • toleranceMinorinteger“Accepted |residual| per settlement in minor units (default 0 = exact).”
    • nearMissToleranceMinorinteger“Largest residual searched when reporting the closest near-miss for an unmatched settlement.”
    • maxLagDaysinteger“An item may settle at most this many days after its date.”
    • limitsobject
  • cra-exploit-clockon 1 other server

    “CRA Exploited-Vulnerability Evidence and Art.”

    6 inputs
    • sbomobject or string“CycloneDX 1.4-1.6 or SPDX 2.2/2.3 JSON SBOM, as an object or a JSON string, up to 5 MB.”
    • purlsarray“Alternative to sbom: versioned package URLs, e.g.”
    • productobject“Your product with digital elements; used only to fill the draft fields (defaults to the SBOM's own product name).”
    • awareness_timestring“When the manufacturer became aware, ISO 8601 with UTC offset (e.g.”
    • fix_available_atstring“When a corrective or mitigating measure became available, ISO 8601 with UTC offset; sets the Art.”
    • issue_recordboolean“Default false.”
  • filing-integrity-checkon 1 other server

    “SEC Filing Integrity Check: XBRL Footing, Tie-Outs, Revisions — Before a figure from a US 10-K or 10-Q is quoted, re-checks it with exact integer arithmetic on SEC XBRL data: balance sheet identity (…”

    7 inputs
    • tickerstring“Exchange ticker, e.g.”
    • cikstring“SEC CIK, digits only.”
    • accessionstring“Accession number of a 10-K or 10-Q, e.g.”
    • fiscal_yearinteger“Fiscal year of the filing's DocumentFiscalYearFocus.”
    • periodstring“FY selects the 10-K; Q1 to Q3 select 10-Qs (there is no Q4 filing).”
    • checksarray“Checks to run; default all six.”
    • rounding_modestring“exact: any nonzero difference fails.”
  • hash-receipton 1 other server

    “Signed hash receipt (Merkle batch, RFC 9162) — Timestamped, signed receipt for up to 256 SHA-256 hashes in one call: an RFC 9162 Merkle root, a per-hash inclusion proof, and the hub's W3C VC + EIP-19…”

    3 inputs, 1 required
    • hashesarrayrequired“SHA-256 digests, 64 hex characters each.”
    • proofsboolean“Return an inclusion proof per hash.”
    • labelstring“Optional caller label (run id, job id) included in the signed receipt.”
  • unicode-checkon 1 other server

    “Unicode smuggling check for strings (prompts, tool args, URLs) — Checks up to 100 strings in one call against the 19 deterministic rules of unicode-safety-check: bidi controls (Trojan Source), invisi…”

    2 inputs, 1 required
    • stringsarrayrequired“Up to 200000 characters in total.”
    • kindstring“text (default): prose, only critical findings block.”
  • mcp-tool-pinon 1 other server

    “MCP tool pin: detect changed tool definitions (rug pulls) and hidden Unicode — Send an MCP server's tools/list result (up to 200 tools) and, after the first call, the hashes you approved.”

    3 inputs, 1 required
    • toolsarrayrequired“The tools array from an MCP tools/list response, as received.”
    • approvedManifestHashstring“manifestHash from the call you approved.”
    • approvedToolsobject“Map of tool name to the per-tool hash you approved; enables the added/removed/changed diff.”
  • “DOI check: exists, retracted, or fabricated (batch of 20) — Checks up to 20 DOIs in one call against Crossref (including its Retraction Watch notices), OpenAlex and the doi.org Handle registry.”

    1 input, 1 required
    • doisarrayrequired“Bare DOIs, doi: prefixes or https://doi.org/ URLs.”
  • open-badges-verifieron 1 other server

    “Open Badges 2.0 / 3.0 credential verifier — Verifies an Open Badges credential end to end and says what could and could not be confirmed.”

    5 inputs
    • credential“The credential or assertion as a JSON object (or the same as a JSON string, or a compact JWS string).”
    • jwsstring“A compact JWS: an Open Badges 3.0 VC-JWT or an Open Badges 2.0 signed assertion.”
    • urlstring“https URL of a hosted Open Badges 2.0 assertion or a hosted 3.0 credential.”
    • imagestring“A baked badge image, base64 (data URLs accepted): a PNG with an openbadges iTXt chunk, or an SVG with an openbadges:assertion or openbadges:credential element.”
    • recipientIdentitystring“Optional: the recipient's email or other identity to compare against the badge's recipient, including salted sha256$ and md5$ hashes.”
  • “Selective PII redaction with a self-check — Redacts detected personal data at the level you choose and rescans the output with the same rules.”

    10 inputs, 1 required
    • textstringrequired“The document text to redact (plain text, Markdown, CSV, JSON or HTML source).”
    • levelinteger“Cumulative preset, default 1.”
    • categoriesarray“Exact set of categories to redact; replaces the level preset when given.”
    • includearray“Categories to add to the level preset.”
    • excludearray“Categories to remove from the level preset.”
    • minDigitRuninteger“Also redact every run of at least this many digits (spaces, dots and hyphens between digits count as part of the run).”
    • termsarray“Words or phrases to redact wherever they appear (business names, project names, people you already know).”
    • keeparray“Strings that must never be redacted, such as your own email address or company name.”
    • stylestring“label (default): [REDACTED:SSN].”
    • useModelboolean“Add a language-model pass for names, organizations and addresses (when those categories are on).”
  • literary-agent-scouton 1 other server

    “Literary Agent Scout: quoted wish-list matches with query status and fee checks — For an author with a book to query, finds literary agents and agencies on the agencies' own websites, reads their gui…”

    4 inputs, 1 required
    • manuscriptobjectrequired
    • pagesarray“Agency submission, wish-list or agent-bio pages you already found.”
    • discoverboolean“Search the web for more agencies (default true).”
    • max_resultsinteger“Default 5.”
  • property-riskon 1 other server

    “Property Hazard & Site Risk Report — Before an agent recommends, underwrites or screens a US property, reads free public federal hazard data for a street address or lat/lon: Census geocode, FEMA Nati…”

    4 inputs
    • addressstring“US street address with city and state or ZIP, e.g.”
    • latnumber“Latitude in WGS84 degrees; give with lon instead of address.”
    • lonnumber“Longitude in WGS84 degrees; give with lat.”
    • intended_usestring“Optional.”
  • farmland-soil-reporton 1 other server

    “Farmland Soil, Water & Drought Report — Before buying, leasing or planting a US parcel, reads the USDA NRCS soil survey at a point (lat/lon or US address): map unit, prime farmland class, land capabi…”

    4 inputs
    • latnumber“WGS84 latitude.”
    • lonnumber“WGS84 longitude.”
    • addressstring“US street address, geocoded by the US Census geocoder.”
    • usestring“Intended use to rate.”
  • property-violations-historyon 1 other server

    “Property Code-Violation & Lien History (Open-Data Cities) — Before buying, leasing or insuring a US property, reads the city's own open-data code-enforcement records for one address (or a NYC BBL/BIN…”

    7 inputs
    • addressstring“US street address with city and state, e.g.”
    • citystring“City, when not inside address.”
    • statestring“Two-letter state, when not inside address.”
    • zipstring“ZIP code (informational; not used to widen a match).”
    • bblstring“NYC borough-block-lot, 10 digits.”
    • binstring“NYC building identification number, 7 digits.”
    • lookback_yearsinteger“Years of history to read (default 10).”
  • regional-economy-briefon 1 other server

    “Regional Economy & Trade Brief — Given a US state, county or metro (name, FIPS or CBSA), an industry (NAICS code or description) and a role (retailer, logistics, cfo, lender, other), reads BLS LAUS a…”

    5 inputs, 3 required
    • regionstringrequired“A US state, county or metropolitan area by name ("Ohio", "Travis County, TX", "Phoenix metro"), state FIPS (39), county FIPS (48453) or metro CBSA code (38060).”
    • regionTypestring“Disambiguates a name that is both a county and a metro or state.”
    • industrystringrequired“NAICS code (44-45, 722, 4841) or a plain description ("restaurants", "trucking").”
    • rolestringrequired“Who the brief is for.”
    • lookbackYearsinteger“Years of history used for z-scores (default 5).”
  • regulatory-change-briefon 1 other server

    “Regulatory Change Brief (Federal Register, EDGAR, Dockets) — Given an industry or topic and optional agencies, CFR parts, terms and companies, pulls recent US regulatory changes from official free so…”

    8 inputs
    • industrystring“Industry or topic, e.g.”
    • agenciesarray“Agency names, acronyms or Federal Register slugs, e.g.”
    • cfr_partsarray“CFR parts, e.g.”
    • sic_codesarray“SIC codes; industry context only, registrants are not enumerated by SIC.”
    • companiesarray“Company names, tickers or CIKs whose recent SEC filings (8-K items, 10-K/Q) to list.”
    • termsarray“Federal Register search phrases, e.g.”
    • window_daysinteger“Publication window ending today, 1 to 180 days (default 30).”
    • focusstring“Weights ranking and the impact assessment toward operations, reporting or enforcement.”
  • infrastructure-pipeline-briefon 1 other server

    “Grid, Tower & Infrastructure Pipeline Near a Site — Screens a US site (latitude/longitude or Census-geocoded address) within a radius (default 10, max 50 miles) using primary public data: operating a…”

    6 inputs
    • latitudenumber“WGS84 latitude of the site (United States and territories).”
    • longitudenumber“WGS84 longitude of the site.”
    • addressstring“US street address, geocoded with the Census Bureau geocoder.”
    • radius_milesnumber“Search radius in miles (default 10, clamped to at most 50).”
    • focusstring“Which screening signals to emphasise.”
    • window_yearsinteger“Window for capacity added within the radius (default 3 years).”
  • patch-anchoron 1 other server

    “Apply a unified-diff hunk or search/replace edit to a file by content, refusing ambiguity — Applies unified-diff hunks (wrong line numbers are fine) or search/replace blocks to a supplied file text a…”

    3 inputs, 1 required
    • filestringrequired“Current file text, at most 524288 UTF-8 bytes and 100000 lines.”
    • diffstring“Single-file unified diff, at most 64 hunks and 400 anchor lines each.”
    • editsarray“Search/replace blocks, matched as whole lines against the original file; all are located before any is applied.”
  • edit-anchor-checkon 1 other server

    “Check that an edit's old-string occurs exactly once in a file, with match contexts — Counts how many times an old-string occurs in a supplied file text (as a replace-in-file tool would see it) and re…”

    3 inputs, 2 required
    • filestringrequired“File text, at most 524288 UTF-8 bytes and 100000 lines.”
    • oldStringstringrequired
    • contextLinesinteger“Lines of context before and after each listed match.”
  • retry-admissibilityon 1 other server

    “Decide whether a failed HTTP call may be retried, must be reconciled, or must not be repeated — Given a request's method, how it ended (response status, timeout, reset, refused), idempotency-key evid…”

    12 inputs, 2 required
    • methodstringrequired“HTTP method, case-sensitive (GET, POST, ...).”
    • endedstringrequired“How the attempt ended.”
    • statusinteger“Required when ended is 'response'.”
    • requestSentstring“Whether request bytes reached the network.”
    • idempotencyKeyobject“Caller-asserted evidence: the engine knows no vendor's key semantics.”
    • retryAfterstring“Retry-After header value.”
    • attemptinteger“1-based number of the attempt that just ended.”
    • automaticboolean“True when the retry would be issued automatically (library or proxy) rather than by a deliberate decision.”
    • previousAttemptWasAutomaticRetryboolean
    • actorstring
    • asOfstring“RFC 3339 instant; needed only to turn a Retry-After HTTP-date into seconds.”
    • policyobject
  • http-outcomeon 1 other server

    “Classify an HTTP response as success, retry, reconcile or stop, with the wait it asks for — Classifies one HTTP response (method, status, headers) as success / retry / reconcile / stop for an agent t…”

    7 inputs, 2 required
    • methodstringrequired
    • statusintegerrequired
    • headersarray“Response headers as name/value pairs (names compared case-insensitively).”
    • delayHeaderobject“Which header carries the wait and in what dialect.”
    • vendorRulesarray“First matching rule wins.”
    • idempotencyKeyobject
    • asOfstring“RFC 3339 instant; needed to turn an HTTP-date or epoch delay into seconds.”
  • mutation-intenton 1 other server

    “Diff a before/after JSON write for deletes, null-vs-omit and emptied arrays against protected paths — Compares the JSON document an agent read (before) with the one it is about to write (after) and l…”

    4 inputs, 2 required
    • beforerequired“JSON value as last read.”
    • afterrequired“JSON value about to be written.”
    • protectedPathsarray“JSON Pointers that must not change at all; a "*" token matches any one key or index.”
    • allowDestructivearray“JSON Pointers ("*" wildcard) under which deletes, emptied containers and type changes are intended.”
  • idempotency-fingerprinton 1 other server

    “Derive a stable idempotency fingerprint from declared identity fields and flag volatile fields — Hashes the fields you declare as the identity of an operation (JSON Pointers into each request) with R…”

    4 inputs, 2 required
    • requestsarrayrequired
    • identityarrayrequired“JSON Pointers whose values define the operation's identity.”
    • volatilearray“JSON Pointers declared to change per attempt (timestamps, nonces, request ids).”
    • scopestring“Mixed into the hash (for example operation name and tenant) so equal bodies in different scopes get different fingerprints.”
  • update-dialecton 1 other server

    “What do omitted, null, [] and "" mean in this PATCH body under merge-patch, JSON Patch or a declared dialect?”

    5 inputs, 2 required
    • dialectstringrequired“merge-patch = RFC 7396, json-patch = RFC 6902 (payload is an array of operations), caller = semantics in callerSemantics.”
    • payloadrequired“The PATCH body.”
    • target“Current document, if available.”
    • intentsarray
    • callerSemanticsobject“Required when dialect is 'caller': what each payload form means in that API.”
  • pagination-loopon 1 other server

    “Detect repeated cursors, duplicate-only pages and no progress in a pagination scan — Takes the pages an agent has fetched so far (cursor used, next cursor returned, item ids) and finds the failures t…”

    2 inputs, 1 required
    • pagesarrayrequired
    • declaredobject
  • compensation-coverageon 1 other server

    “Check that every write step in a multi-step plan has an undo step, and give the rollback order — For an agent plan made of steps with declared effects (read or write), checks every write in the plan,…”

    2 inputs, 1 required
    • stepsarrayrequired
    • completedarray“Step ids completed so far, in completion order.”
  • workflow-transitionon 1 other server

    “Is this state transition allowed by the caller's workflow definition, and what is allowed instead?”

    5 inputs, 3 required
    • transitionsarrayrequired
    • terminalarray“States with no outgoing transitions allowed even if listed.”
    • currentstringrequired
    • requestobjectrequired“Give event, to, or both.”
    • factsarray
  • deadline-feasibilityon 1 other server

    “Can this plan of steps finish inside the remaining time, in the expected case and the worst case?”

    3 inputs, 2 required
    • stepsarrayrequired
    • remainingMsintegerrequired“Time left to the hard deadline, measured by the caller.”
    • overheadMsinteger“Fixed time to reserve for settlement, serialization, etc.”
  • approval-invalidationon 1 other server

    “Does a change to the approved thing invalidate the approval under a materiality policy?”

    9 inputs, 2 required
    • approvedrequired“The approved snapshot (JSON).”
    • currentrequired“The version about to be executed (JSON).”
    • policyobject
    • approvedRevisioninteger
    • currentRevisioninteger
    • requireSameRevisionboolean“Default true when either revision is given (a missing partner gives unknown): an approval for another revision does not cover this one.”
    • approvedAtstring“RFC 3339 instant.”
    • validForSecondsinteger
    • asOfstring“RFC 3339 instant for the expiry check; no clock is read.”
  • quota-reservation-checkon 1 other server

    “Would this request fit in the remaining quota, given a snapshot and pending reservations?”

    6 inputs, 4 required
    • quotaobjectrequired
    • pendingarray
    • requestobjectrequired
    • snapshotAtstringrequired“RFC 3339 instant the quota numbers were read.”
    • asOfstringrequired“RFC 3339 instant of the decision (no clock is read).”
    • maxSnapshotAgeSecondsinteger
  • dedup-windowon 1 other server

    “Group webhook deliveries by identity within a time window and decide: process, dedupe, retry, reconcile or abstain — Given previously seen deliveries (identity, receivedAt, payload or digest, handlin…”

    4 inputs, 3 required
    • historyarrayrequired
    • incomingobjectrequired
    • windowSecondsintegerrequired
    • windowModestring“from-first (default): a group's window starts at its first delivery.”
  • transcript-validatoron 1 other server

    “Check tool-call / tool-result pairing and ordering in an LLM transcript (Anthropic, OpenAI Chat, OpenAI Responses) — Validates a message list before it is sent to Anthropic Messages, OpenAI Chat Comp…”

    3 inputs, 2 required
    • providerstringrequired
    • messagesarrayrequired
    • expectCompleteboolean“Default true: a trailing tool call without a result is a defect.”
  • cache-key-checkon 1 other server

    “Check that a result-cache key contains every input that changes the result, and nothing volatile — Given the inputs of a cached computation (each declared as influencing the output or not, optionally…”

    5 inputs, 2 required
    • inputsarrayrequired
    • keyPartsarrayrequired“Names of the inputs the key is built from.”
    • scopestring“Namespace mixed into the digest.”
    • privateboolean“The result is per-tenant or per-user.”
    • tenantInputstring“Name of the input that identifies the tenant or user; required in the key when private.”
  • delegation-contract-checkon 1 other server

    “Check that a sub-agent delegation states objective, acceptance criteria, budget, evidence and stop conditions — Checks the brief an agent is about to hand to another agent: the required parts are pre…”

    7 inputs
    • objectivestring
    • acceptanceCriteriaarray
    • budgetobject
    • evidenceRequiredarray“What the delegate must return as proof (links, test output, file paths).”
    • stopConditionsarray“When the delegate must stop and report (done, blocked, budget spent).”
    • outputFormatstring
    • requirearray“Parts that must be present.”
  • permission-intersectionon 1 other server

    “Effective permissions of a delegated agent: requested ∩ user ∩ parent, minus explicit denials — Computes what a sub-agent may actually do: the permissions it requested, intersected with what the end …”

    5 inputs, 3 required
    • requestedarrayrequired“Permissions the delegate asks for.”
    • userarrayrequired“Permissions held by the end user.”
    • parentarrayrequired“Permissions held by the delegating agent.”
    • deniedarray“Explicit denials; they win over any grant.”
    • impliesarray
  • artifact-invalidatoron 1 other server

    “Which derived artifacts must be rechecked after these inputs changed?”

    2 inputs, 2 required
    • artifactsarrayrequired
    • changedarrayrequired
  • assumption-conflicton 1 other server

    “Find assumptions that disagree across agents (currency, timezone, version, customer id, ...) — Takes assumptions that several agents or steps hold about the same fact (key, value, who) and reports ev…”

    3 inputs, 1 required
    • assumptionsarrayrequired
    • requiredKeysarray“Keys every listed agent must state.”
    • agentsarray“Agents expected to state the required keys.”
  • test-exit-interpreton 1 other server

    “Interpret a test run: pass, no-tests, skipped, flaky, infra-failure from runner, exit code and counts — Reads a finished test run (runner, exit code, optional version, flags, caller-parsed counts, op…”

    9 inputs, 1 required
    • runnerstringrequired
    • exitCodeinteger“Process exit status.”
    • signalstring“Terminating signal name, e.g.”
    • timedOutboolean“True when the harness gave up waiting.”
    • versionstring“Runner version, e.g.”
    • flagsobject
    • countsobject“Counts parsed by the caller from the runner's own report.”
    • outputstring“go test output (only ok, FAIL, --- FAIL and panic: lines are read).”
    • attemptExitCodesarray“Exit codes of repeated runs of the same tests, to detect flakiness.”
  • json-patch-conflicton 1 other server

    “Conflicts between two to four RFC 6902 JSON Patches made against the same document — Takes one base document and 2 to 4 JSON Patch (RFC 6902) operation lists written against it and reports, per pair,…”

    2 inputs, 2 required
    • documentrequired“The base document both patches were written against (any JSON value).”
    • patchesarrayrequired
  • duplicate-key-auditon 1 other server

    “Duplicate JSON object keys found in raw text, before a parser drops them — Scans raw JSON text (RFC 8259) for repeated object member names at any depth, including inside arrays and keys spelled diffe…”

    1 input, 1 required
    • textstringrequired“Raw JSON text, up to 200000 characters and 64 levels of nesting.”
  • union-branchon 1 other server

    “Which oneOf / anyOf branch a JSON value matches, or why several or none do — Evaluates a JSON value against every branch of a oneOf or anyOf in a caller-supplied JSON Schema 2020-12 (or OpenAPI schem…”

    4 inputs, 2 required
    • schemarequired“The root schema; $ref targets are resolved inside it.”
    • valuerequired“The JSON value to classify.”
    • atstring“JSON pointer to the subschema holding the union ("" for the root, "/properties/pet" for a nested one).”
    • keywordstring“Required only when the subschema has both.”
  • cross-field-ruleson 1 other server

    “Check caller-declared rules across fields of a JSON record: end after start, conditional required, exactly one of — Evaluates up to 100 rules you declare over one JSON document and reports, per rule,…”

    3 inputs, 2 required
    • datarequired“The JSON document the rules apply to.”
    • rulesarrayrequired
    • onMissingstring“Missing or null compare operand: unknown (default), fail or skip.”
  • lossy-conversionon 1 other server

    “Does this value survive conversion to another numeric or spreadsheet type?”

    3 inputs
    • samplesarray“Raw JSON scalar literals exactly as written, e.g.”
    • targetsarray“Target types: float64, float32, int8, int16, int32, int64, uint8, uint16, uint32, uint64, numeric(p,s), decimal128(p,s), decimal256(p,s), parquet-decimal(p,s),…”
    • pairsarray“Identifier or text values before and after a round trip through another system.”
  • schema-repairon 2 other servers

    “Repair a JSON value toward a schema using only the coercions the caller declares — Validates a JSON value against a caller-supplied JSON Schema 2020-12 and applies only the coercions you list (for ex…”

    3 inputs, 3 required
    • schemarequired“The schema the value must satisfy.”
    • valuerequired“The JSON value to repair.”
    • coercionsarrayrequired“Coercions you allow.”
  • schema-witnesson 1 other server

    “One valid and one invalid example for each constraint in a JSON Schema — Walks a caller-supplied JSON Schema 2020-12 and, for every constraint keyword (type, enum, const, minimum, maximum, exclusiveM…”

    2 inputs, 1 required
    • schemarequired“The schema to generate examples for.”
    • maxConstraintsinteger“Stop after this many constraints (default 100).”
  • csv-roundtripon 1 other server

    “Will this CSV survive a typed round trip and a spreadsheet: leading zeros, big ids, dates, formulas, empty vs null — Parses CSV text (RFC 4180, caller dialect) against a column type map and reports, …”

    5 inputs, 1 required
    • textstringrequired“CSV text, up to 200000 characters.”
    • dialectobject
    • types“Object mapping column name to one of string, identifier, integer, decimal, boolean, date, datetime (max 200).”
    • nullTokenstring“Text that means null (e.g.”
    • spreadsheetboolean“Check Excel/Sheets coercion hazards (default true).”
  • “Detect a CSV file's delimiter, quote, header row and broken header names — Detects the delimiter (comma, semicolon, tab, pipe), quote character, line terminator, BOM, header row offset (preamble line…”

    1 input, 1 required
    • textstringrequired“CSV text, up to 200000 characters.”
  • enum-canonicalizeon 1 other server

    “Map free-text values onto a closed set of allowed values, or abstain — Maps each input string onto one member of a closed caller-supplied set using, in order: exact match, caller aliases, a determini…”

    5 inputs, 2 required
    • valuesarrayrequired“Strings to canonicalize.”
    • allowedarrayrequired“The closed set of canonical values.”
    • aliasesarray“Caller synonyms; each canonical must be in allowed.”
    • maxDistanceinteger“Largest edit distance accepted (default 2).”
    • caseSensitiveboolean“Skip case, accent and punctuation folding (only NFKC and whitespace collapse).”
  • config-migrationon 1 other server

    “Migrate a v1 config to a v2 schema with an explicit mapping, and list what was dropped or defaulted — Applies a declared mapping (from pointer, to pointer, optional transform such as string-to-number…”

    5 inputs, 3 required
    • v1required“The old config (any JSON value).”
    • v2Schemarequired“The new config's schema.”
    • mappingarrayrequired
    • carryDeclaredboolean“Copy unmapped v1 values to the same pointer when v2 declares that property (default true).”
    • applyDefaultsboolean“Fill missing v2 properties from schema defaults (default true).”
  • openapi-sliceon 1 other server

    “Slice one operation out of an OpenAPI 3.0 or 3.1 document with every component it needs — Extracts one operation (path plus HTTP method, matching templated paths like /pets/{id}) from an OpenAPI 3.0.…”

    4 inputs, 2 required
    • spec“The OpenAPI document as a JSON object (use specText for YAML).”
    • specTextstring“The OpenAPI document as JSON text (up to 400000 characters) or YAML text (up to 50000 characters).”
    • pathstringrequired“Concrete or templated path, e.g.”
    • methodstringrequired
  • schema-compaton 1 other server

    “Breaking-change diff between two JSON Schemas or OpenAPI documents, and whether cached calls still validate — Compares an old and a new JSON Schema 2020-12 (or two OpenAPI 3.0/3.1 documents) and list…”

    5 inputs, 3 required
    • beforerequired“The old schema, or old OpenAPI document.”
    • afterrequired“The new schema, or new OpenAPI document.”
    • kindstringrequired
    • rolestring“json-schema only: request (default) or response; OpenAPI compares each side in its own role.”
    • callsarray
  • join-cardinalityon 1 other server

    “Row multiplication, unmatched keys and uniqueness violations before a table join — Takes the join keys of two tables (every row's key, or distinct keys with row counts) and computes the exact output …”

    5 inputs, 3 required
    • leftobjectrequired
    • rightobjectrequired
    • joinTypestringrequired
    • expectobject
    • normalizeobject“Normalization your pipeline applies to string keys before joining.”
  • sentinel-valueson 1 other server

    “Placeholder values hiding as data: caller-declared sentinels and likely candidates — Scans columns of values for sentinels.”

    2 inputs, 1 required
    • columnsarrayrequired
    • dictionaryarray“Values you know are sentinels.”
  • metric-comparabilityon 1 other server

    “Whether two metric definitions measure the same thing, and which fields differ — Compares two structured metric definitions field by field (numerator, denominator, aggregation, weighting, population,…”

    3 inputs, 2 required
    • aobjectrequired
    • bobjectrequired
    • modestring“drift: a is the previous definition and b the current one under the same name.”
  • context-packon 1 other server

    “Pick context blocks that fit a token budget, keeping mandatory blocks and their dependencies — Chooses which context items an agent should put into a prompt without exceeding a token budget: every ma…”

    4 inputs, 2 required
    • itemsarrayrequired“Up to 500 items, 300000 characters of text in total.”
    • budgetintegerrequired“Maximum total tokens (including perItemOverhead per included item).”
    • tokenizerstring“o200k_base or cl100k_base.”
    • perItemOverheadinteger“Tokens added per included item for separators or wrappers.”
  • citation-spanon 1 other server

    “Locate quoted text in a source with exact offsets, or classify it as normalized, elided, paraphrased or absent — Finds each quote an agent attributes to a source text and returns where it sits: exact…”

    6 inputs, 2 required
    • sourcestringrequired“Text the quotes are claimed to come from.”
    • quotesarrayrequired“Up to 50 quotes, 40000 characters in total.”
    • ignoreCaseboolean“Also tolerate case differences (reported as a normalization).”
    • toleratearray“Normalizations that still count as a match.”
    • exactOnlyboolean“Count only byte-identical matches as pass; normalized matches become fail.”
    • minLengthinteger“Quotes shorter than this many characters (after trimming quote marks) are too-short and give unknown.”
  • constraint-carryoveron 1 other server

    “Check that earlier constraints (numbers, dates, codes, quoted terms, negations) survive into a later plan or summary — Takes the constraints an agent was given (budget caps, deadlines, identifiers, p…”

    2 inputs, 2 required
    • constraintsarrayrequired“Up to 50; 20000 characters of constraint text in total.”
    • targetstringrequired“The later artifact that must still honor the constraints.”
  • evidence-bundle-checkon 1 other server

    “Check that every claim in an evidence bundle has enough independent, fresh, quote-verified support — Checks a bundle an agent assembled before answering: each claim must be backed by at least N evide…”

    5 inputs, 2 required
    • claimsarrayrequired“Claims to support.”
    • evidencearrayrequired“Up to 300 items; 300000 characters of text in total.”
    • asOfstring“Reference instant (ISO 8601) for age checks; required with maxAgeDays.”
    • maxAgeDaysinteger“Evidence published longer ago than this (relative to asOf) is stale.”
    • requireQuotesboolean“Evidence without a verifiable quote does not count as support.”
  • syndication-hinton 1 other server

    “Detect near-duplicate passages (syndicated or copied text) so repeated sources are not counted as independent — Compares up to 30 passages an agent collected and reports which pairs share word-shingl…”

    4 inputs, 1 required
    • passagesarrayrequired“Up to 30; 300000 characters in total.”
    • shingleWordsinteger“Words per shingle.”
    • jaccardThresholdnumber“Pairs at or above this Jaccard similarity are flagged.”
    • containmentThresholdnumber“Pairs where this share of the smaller passage's shingles appear in the other are flagged (catches an excerpt of a longer copy).”
  • hedge-extracton 1 other server

    “Extract hedging and certainty cues (may, probably, clearly, approximately) from text with offsets — Finds hedge and booster cues in an agent's or source's text using a fixed English lexicon (modals, …”

    2 inputs, 1 required
    • textstringrequired“Text to scan.”
    • extraCuesarray“Caller cues added to the lexicon.”
  • negation-scopeon 1 other server

    “Find negation cues and the words they cover; report whether given terms fall inside a negation scope — Applies NegEx-style rules (the English termset of negspacy, MIT, derived from NegEx) to text: fi…”

    3 inputs, 1 required
    • textstringrequired“Text to analyze.”
    • targetsarray“Terms to classify (literal, case-insensitive, whole words).”
    • windowinteger“Words a cue covers (NegEx uses 5).”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. The first 100 of 262 tools are listed. Read 2026-11-16.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
82% of 1,288
Tools with a description
100% of 262
Typical description length
468 characters

The tool set

Counted from the listing

Tools
262
Size of the list
about 120,727 tokens for an agent to load (characters ÷ 4)
Naming
255 of 262 names use kebab-case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 262 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-16 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://agents.writerslogic.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "writerslogic-agents": {
      "url": "https://agents.writerslogic.com/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "writerslogic-agents": {
      "type": "http",
      "url": "https://agents.writerslogic.com/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"writerslogic-agents","type":"http","url":"https://agents.writerslogic.com/mcp"}'
Claude Code
claude mcp add --transport http writerslogic-agents https://agents.writerslogic.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "writerslogic-agents": {
      "type": "streamableHttp",
      "url": "https://agents.writerslogic.com/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "writerslogic-agents": {
      "httpUrl": "https://agents.writerslogic.com/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.writerslogic-agents]
url = "https://agents.writerslogic.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "writerslogic-agents": {
      "url": "https://agents.writerslogic.com/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://agents.writerslogic.com/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

What do the published files and outside lists say?

Read as text · nothing run · no tool called

Package files

  • MCP SDK in the package files. Not read yet: added with the next daily run.
  • Build workflow. Not read yet: added with the next daily run.

Outside lists

  • CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-16. This product uses the NVD API but is not endorsed or certified by the NVD.
  • GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-16. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-16. Source: read 2026-11-16.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-16. Source: read 2026-11-16.

Own host

  • security.txt. No security.txt at https://agents.writerslogic.com/.well-known/ (HTTP 404, 2026-11-16). security.txt found at https://writerslogic.com/.well-known/security.txt (Contact given; expires 2027-04-12). Source: agents.writerslogic.com/.well-known/security.txt · read 2026-11-16.
  • A2A agent card. An A2A agent card is published at https://agents.writerslogic.com/.well-known/agent-card.json (name, skills, url). An A2A agent card is published at https://writerslogic.com/.well-known/agent-card.json (name, skills, url). Source: agents.writerslogic.com/.well-known/agent-card.json · read 2026-11-16.

Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint agents.writerslogic.com/mcpSession openedmatchesour test · 2026-11-16
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-16
Repository github.com/writerslogic/ai-agentsDoes not open (not found or private)differsapi.github.com · 2026-11-16

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace
com.writerslogic.agents · 7 servers
Repository
github.com/writerslogic/ai-agents — does not open publicly
Security policy
none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-11-16; security policy read from GitHub · 2026-11-16.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe linked repository returned HTTP 404: it does not exist or is private.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-16 (security policy 2026-11-16). No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about com.writerslogic.agents/writerslogic-agents

Answered from the data above

Who publishes com.writerslogic.agents/writerslogic-agents?

The registry ties the namespace com.writerslogic.agents to the domain agents.writerslogic.com; only its owner can publish under it. Its linked repository, github.com/writerslogic/ai-agents, does not open publicly (missing or private). These are facts from the registry and GitHub, not a rating.

Is com.writerslogic.agents/writerslogic-agents safe to install?

We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: The repository it links to does not open publicly, so its code cannot be inspected through that link. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does com.writerslogic.agents/writerslogic-agents need an API key or sign-in?

It opened a session without any credential on 2026-11-16. The registry entry declares no required credential; no declaration is not a guarantee.

Has com.writerslogic.agents/writerslogic-agents been security tested?

Partly. 2 of the 14 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.

Does com.writerslogic.agents/writerslogic-agents publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Where is the source code of com.writerslogic.agents/writerslogic-agents?

The registry links to github.com/writerslogic/ai-agents, but that link does not open publicly, so the code cannot be inspected through it.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-16
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 2
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 4
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 2026-11-16, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 38 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 262 tools, 0 resources, 0 prompts.
  4. 1,331 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-16; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
does not apply
no existing GitHub repository
Hosting type
registry · 2026-11-16
MCP capability
tools
our test · 2026-11-16
Transport
streamable HTTP
registry · 2026-11-16
Required credentials
none declared
registry · 2026-11-16 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-11-16
Lifecycle status
registry · 2026-11-16
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
not stated
repository link is dead (HTTP 404), so activity cannot be read
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-11-16

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “com.writerslogic.agents/writerslogic-agents: MCP server record.” Data checked 2026-11-16. https://protocolprobe.com/mcp/servers/com.writerslogic.agents/writerslogic-agents

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/com.writerslogic.agents/writerslogic-agents)](https://protocolprobe.com/mcp/servers/com.writerslogic.agents/writerslogic-agents)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).

Write to hello@protocolprobe.com · corrections log · methodology