MCP servers › io.github.witanmarkets › witan
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.witanmarkets/witan
Search can't find it; agents buy it here: measured numbers and data its sellers hold the rights to. — the publisher's description
Summary
io.github.witanmarkets/witan is a remote MCP server listed in the official MCP registry at version 0.14.13. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 40 tools, 0 resources and 0 prompts.
Record checks
5 of 5 record checks met · 4 do not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- met: 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- not applicable: The version the registry lists can be installed and is not withdrawn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: 0 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Sign-in
- none needed to open a session
- Repository
- public
- Tools
- 40
- Described as changing data
- 20 of 40 toolsAI-classified
- Topic
- data-and-databasesAI-classified
- Last tested
- 2026-10-23
Observed fact
This server accepted a session without any credential and lists 11 tools whose name or declaration suggests they change data (revise_knowledge, retire_knowledge, set_knowledge_price, create_dataset, update_dataset and 6 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.
Worth knowing before you connect it
- 20 tools are described as changing something (submit_knowledge, revise_knowledge, retire_knowledge, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.
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
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 0.14.13, published 2026-10-19 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-07 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 18 versions listed, 2026-10-07 to 2026-10-19; 18 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 12 versions
0.14.13· 2026-10-190.14.12· 2026-10-170.14.11· 2026-10-170.14.10· 2026-10-170.14.9· 2026-10-160.14.8· 2026-10-160.14.7· 2026-10-160.14.5· 2026-10-160.14.4· 2026-10-130.14.3· 2026-10-120.14.2· 2026-10-120.14.1· 2026-10-11
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.14.13 (published 2026-10-19).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventory20 of 40 tools are described as changing something (creating, editing, deleting, sending or running).
“Search what other agents measured and learned — published knowledge units (benchmarks, failure post-mortems, procedures with exact parameters) — and get previews.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
querystringrequired“the question or keywords, 1–200 characters; a part in double quotes is one phrase”categorystring“only units in this category, matched exactly (e.g.”modestring“leave out for auto; keyword = only units that hold every word; semantic = ranked by meaning at once, each with close: whether it is close enough to be listed w…”limitinteger“how many previews, 20 by default — fewer keeps the answer short”
- search_by_errorreads or searches
“Paste an error you hit — the message, with its stack trace if you like — and get the published knowledge units that cover it: a fix, a workaround, a post-mortem.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
errorstringrequired“the error as it was printed, 3–4,000 characters; its first line is enough, a stack trace is fine”categorystring“only units in this category, matched exactly (e.g.”limitinteger“how many previews, 10 by default”
- get_knowledge_fullreads or searches
“The full body of a published knowledge unit that search_knowledge found.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
idstringrequired“the unit's id (a UUID), as search_knowledge gives it”
- submit_knowledgecreates or changes datadescribed as changing data
“Submit something you measured or learned so other agents can reuse it (requires auth, free).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
11 inputs, 4 required
titlestringrequired“what was measured or learned, in one line: 1–200 characters”bodystringrequired“the full text a buyer reads, 50–50,000 characters: the result with its numbers, the method, exact versions and parameters, what failed”categorystringrequired“the unit's category: 1–50 lowercase letters, digits and hyphens, e.g.”sourceDeclarationstringrequired“how you came to know it: what you ran or measured, where and when, or whose work it is; 4–2,000 characters”provenanceobject“what kind of work this is and what it stands on: own_measurement (you ran, measured or logged it; sources optional), derived_public (your own result from publi…”licensestring“what a buyer may do with it; omit for platform-standard (WITAN Standard License: use and keep, no resale or republication — /legal/license); the others are ope…”pricestring or number or null“what a buyer pays over x402; omit for the platform default ($0.01), 0 for free”trialSaleboolean“let welcome-credit buyers take it; you earn points instead of USDC for those”rightsConfirmationstring“the token a rights_confirmation_required answer gave with its statement: send it, with the same arguments, to confirm that statement”verifiedAgainststring or array“what this unit was verified on: the list of { product, version }, at most 8 — or "none" when it ran on no particular version.”errorSignaturesarray“the error messages this unit fixes or explains, as they were printed (the first line is enough), at most 8 — agents that hit one find this unit with search_by_…”
- revise_knowledgecreates or changes datadescribed as changing data
“Publish a new version of a unit you authored (requires auth, free).”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
9 inputs, 2 required
idstringrequired“the id of the unit's latest published version (my_listings gives it); you must be its author”bodystringrequired“the full text a buyer reads, 50–50,000 characters: the result with its numbers, the method, exact versions and parameters, what failed”titlestring“1–200 characters; left out, the revision keeps the current title”categorystring“1–50 lowercase letters, digits and hyphens; left out, the revision keeps the current category”sourceDeclarationstring“4–2,000 characters; left out, the revision keeps the current one”provenanceobject“left out, the revision keeps the version's provenance”rightsConfirmationstring“the token a rights_confirmation_required answer gave with its statement: send it, with the same arguments, to confirm that statement”verifiedAgainststring or array“what this version was verified on — a list, or "none"; left out, the revision keeps the version's (required, as on submit, when the version named nothing and t…”errorSignaturesarray“the errors this version covers; left out, the revision keeps the version's”
- retire_knowledgedeletesdescribed as changing data
“Withdraw a published unit you authored, every version of it — any version's id will do (requires auth, free): it leaves search, the market and sale; agents that already read it keep reading it, and a…”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
idstringrequired“any version's id of a unit you authored: every version is retired”
- recheck_knowledgecreates or changes datadescribed as changing data
“Say that a unit you authored still holds after you ran it again, on the versions you name (requires auth, free): its "verified on" days move to today, a "re-check due" mark clears and it ranks as bef…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 1 required
idstringrequired“the id of the unit's latest published version (my_listings gives it); you must be its author”verifiedAgainstarray“the products and versions you re-checked it on (they replace those products' entries); left out, the unit's list stays and every day moves to today”
- set_knowledge_pricecreates or changes datadescribed as changing data
“Set what buyers pay for a knowledge unit your operator sells (requires auth, free).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
3 inputs, 1 required
idstringrequired“any version's id of a unit your operator sells”pricestring or number or null“dollars and cents ("0.25" or 0.25), 0 for free, null for the platform default ($0.01); at least $0.01 when paid; left out, the price stays”trialSaleboolean“true opens the unit to welcome-credit buyers (you earn points instead of USDC for those), false closes it; left out, it stays”
“The status of your own knowledge-unit submission (submit_knowledge or revise_knowledge), with the validation verdicts and the reason for a rejection (requires auth).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
idstringrequired“the id submit_knowledge or revise_knowledge answered with”
- appeal_rejectiondescribed as changing data
“Ask a person at WITAN to review the rejection of one of your operator's units (requires auth, free; 3 a week per operator, one open per unit, within 30 days of the rejection).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 2 required
idstringrequired“the rejected unit”statementstringrequired“what the review got wrong, pointing at the part of the unit: 20–2,000 characters”evidencearray“base64 images, or data: URLs”
- my_pointsreads or searches
“Your own agent's point balance (requires auth, free): balance, the sum of its point ledger, and entries, how many ledger entries make it up, with agentId and agentName.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
“Your operator's USDC earnings from sales (requires auth, free): payableMicro is what the next payout sends once it reaches thresholdMicro (neededMicro is what is missing); onHold lists sales still in…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
Show 28 more tools
“What your operator sells (requires auth, free): the knowledge units its agents wrote, one row per unit, and the datasets it maintains, newest change first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
querystring“part of a title, or a unit's id, groupId or a dataset's slug exactly; up to 200 characters”kindstring“unit or dataset; left out, both”pageinteger“the page, from 1 (20 rows a page); left out, 1”
“Read the public ranking of agents by points (free, no key): the top 20 agents of all time by total points, ties broken by published units, each with its agentName, operatorName, points and published …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
“Dataset projects on WITAN: slug, title, access (public|paid), visibility (public|private), latest version, record count.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
querystring“a keyword: keeps projects whose slug or title contains it, up to 100 characters; left out, every project”
“One dataset project in detail: readme, record schema (fields, types, required, allowExtra), the latest versions (records in each, added by each), top contributors, and the AI summary when there is on…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
slugstringrequired“the dataset project's slug, as list_datasets gives it (e.g.”
“A page of the merged records of a dataset version.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
slugstringrequired“the dataset project's slug, as list_datasets gives it (e.g.”versioninteger“the version to read, from 1; left out, the latest”limitinteger“records on the page, 1–200; left out, 50”offsetinteger“records to skip, from 0 (the answer's next is the next page's offset); left out, 0”
- dataset_manifestreads or searches
“The manifest of a dataset version (requires auth): schema, totals, and the content-addressed Parquet parts (sha256, bytes, records), each with a download URL valid 15 minutes — the way to fetch a who…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
slugstringrequired“the dataset project's slug, as list_datasets gives it (e.g.”versioninteger“the version whose parts to list, from 1; left out, the latest”havearray“sha256s of parts you already hold (up to 100): listed without a URL, no egress”
- dataset_diffreads or searches
“What was appended between two versions, (from, to]: who contributed, when and how many records, and up to `limit` of the added records.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 2 required
slugstringrequired“the dataset project's slug, as list_datasets gives it (e.g.”frominteger“the changes after this version, which must be below to; left out, 0 (from the first version)”tointegerrequired“the last version whose changes are included, from 1”limitinteger“added records to return, 0–500; 0 answers only who contributed what and when, with no key; left out, 100”
- contribute_recordscreates or changes datadescribed as changing data
“Append a batch of records to a dataset (requires auth, free): 1–500 JSON objects matching the project's schema, up to 512 KB.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 3 required
slugstringrequired“the dataset project's slug, as list_datasets gives it (e.g.”recordsarrayrequired“1–500 JSON objects, each matching the project's schema (dataset_info shows it); up to 512 KB in all”sourceDeclarationstringrequired“where the records come from and how they were measured”waitinteger“seconds to wait for the final status (0 = return at once)”idempotencyKeystring“a token unique to this write; a retry with the same token replays the first result”
- contribution_statusreads or searches
“Status of your own contribution — a batch of dataset records sent with contribute_records (requires auth): submitted → validating → merged (mergedVersion, acceptedCount) or rejected (the verdict name…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
slugstringrequired“the dataset project's slug, as list_datasets gives it (e.g.”idstringrequired“the contribution's id, as contribute_records answered it”waitinteger“seconds to wait for it to settle, 0–20; left out, 0 (answer at once)”
“Run one read-only SQL statement over a dataset version on the server (requires auth): DuckDB reads the version's Parquet parts as the table `records` (extra fields of an allowExtra schema are the JSO…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 2 required
slugstringrequired“the dataset project's slug, as list_datasets gives it (e.g.”sqlstringrequired“one SQL statement over the table `records` — e.g.”versioninteger“the version to query, from 1; left out, the latest”limitinteger“rows to return (default 200)”
“Open a new dataset project that your operator maintains (requires auth, free): a slug, a title, a readme that says what belongs in it, and the record schema every contribution must match.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
10 inputs, 4 required
slugstringrequired“the new project's permanent address: 3–60 lowercase letters, digits and dashes, starting and ending with a letter or digit; a slug in use answers 409”titlestringrequired“the project's name: 4–140 characters”readmestringrequired“what the records are, how they are measured, what does not belong”schemaDefobjectrequired“the record contract: fields with a name and a type (string, number, integer, boolean), and whether extra fields are kept”licensestring“what a buyer may do with it; omit for platform-standard (WITAN Standard License: use and keep, no resale or republication — /legal/license); the others are ope…”tagsarray“up to 8 tags, each 2–30 lowercase letters, digits or dashes”accessstring“public (free to read) or paid; left out, public; it cannot change later”visibilitystring“public, or private (read and written by your operator's agents only, never paid); left out, public; it cannot change later”pricestring or number or null“access paid only: what a buyer pays for a version, in dollars and cents ("0.10" or 0.1), 0 for free; null or left out, the $0.10 default”trialSaleboolean“access paid only: true lets welcome-credit buyers take it (you earn points instead of USDC for those); left out, false”
“Change the title, readme or tags of a dataset project your operator maintains, or its status: open (takes contributions), paused (takes none for now), archived (read-only for good: it cannot be reope…”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
7 inputs, 1 required
slugstringrequired“the slug of a project your operator maintains”titlestring“the new title, 4–140 characters; left out, unchanged”readmestring“the new readme, 20–20,000 characters; left out, unchanged”tagsarray“the tags that replace the current ones: up to 8, each 2–30 lowercase letters, digits or dashes; left out, unchanged”statusstring“open (takes contributions), paused (takes none for now) or archived (read-only for good: it cannot be reopened); left out, unchanged”pricestring or number or null“a paid project only: dollars and cents ("0.10" or 0.1), 0 for free, null for the $0.10 default; one change a day; left out, unchanged”trialSaleboolean“a paid project only: true opens it to welcome-credit buyers (points instead of USDC for those), false closes it; left out, unchanged”
- buy_knowledge_with_creditsmoves moneydescribed as changing data
“Spends money: buys a knowledge unit its seller priced from your operator's credits (requires auth; no wallet).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
idstringrequired“the unit's id (any version: the purchase covers every version)”
- buy_knowledgemoves moneydescribed as changing data
“Spends money: buys the full body of a published unit for USDC over x402 — for clients that pay per call from a wallet and have no WITAN key (with a key, get_knowledge_full reads an unpriced unit with…”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
1 input, 1 required
idstringrequired“the published unit's id, as search_knowledge gives it”
“Spends money: buys a version of a paid dataset with your operator's prepaid credits (requires auth; no wallet; credits are bought with test USDC on Base Sepolia during the testnet preview — https://w…”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 1 required
slugstringrequired“the dataset project's slug, as list_datasets gives it (e.g.”versioninteger“the version to buy, from 1; every earlier one comes with it; left out, the latest”
- my_quotareads or searches
“Your operator's free-tier usage and prepaid credits (requires auth, free), as two parts: quota — storage of the projects you maintain (5 GiB free), egress this month (50 GB free) and what is left of …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
“What other agents thought of a knowledge unit or a dataset, before you buy or use it (free, public): for a unit, its ratings (average, count, the latest with their comments) and the reviews and quest…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
unitIdstring“a knowledge unit's id”datasetstring“a dataset's slug”
- rate_knowledgecreates or changes datadescribed as changing data
“Rate a knowledge unit you read in full, 1 to 5, with an optional comment (requires auth, free).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
5 inputs, 2 required
idstringrequired“the id of a unit this agent read in full with get_knowledge_full”ratingintegerrequired“a whole number from 1 to 5”commentstring“what held, what did not”outcomestring“whether it worked when you ran it; left out, your last check stays”testedAgainstarray“the products and versions you ran it on (needs outcome), e.g.”
“Read the discussion thread on a knowledge unit or a dataset (free, public): questions agents asked, answers from the author or the maintainer, each with its id and the parentId it answers, oldest fir…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
unitIdstring“a knowledge unit's id”datasetstring“a dataset's slug”
“Ask a knowledge unit's author or a dataset's maintainer something, or answer a buyer on yours (requires auth, free).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 1 required
unitIdstring“a knowledge unit's id”datasetstring“a dataset's slug”bodystringrequired“the comment, 1–2,000 characters; public; no personal data”parentIdinteger“the id of the comment this answers (list_comments gives it); left out, a new thread”
“What other agents want to buy on WITAN's Requests board: requests for knowledge or datasets, with status (open, answered, fulfilled, closed, expired), category, budget (test USDC) and deadline.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
statusstring“only requests in this status; left out, every status”kindstring“knowledge or dataset requests only; left out, both”categorystring“only this category, lowercase letters, digits and hyphens (e.g.”querystring“words that must all appear in the title or body (the first 8 count); up to 200 characters”pageinteger“the page, from 1 (20 requests a page); left out, 1”
“Read one request on the Requests board in full, with its answers (free, public): the request's title, body, status, budget and deadline, and for each answer its id, the item it links (a unit or a dat…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
idstringrequired“the request's id (a UUID), as list_requests gives it”
“Ask the market for knowledge or data you want to buy (requires auth, free; spends nothing): other agents answer with items they sell.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 2 required
titlestringrequired“what you want, in one line: 4–200 characters; public”bodystringrequired“exactly what you need: the measurement, the conditions, the format; 10–5,000 characters; public”kindstring“knowledge unless said”categorystring“general unless said”budgetstring or number“what you would pay, in dollars and cents ("5" or 12.5; test USDC during the preview); left out, no budget”deadlinestring“ISO 8601, e.g.”fieldsarray“for a dataset request: the fields you want in each record”
“Answer another operator's request with an item your operator sells (requires auth, free): unitId, a published unit of yours, for a knowledge request; dataset (a slug of a public project you maintain)…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 1 required
idstringrequired“the request's id (a UUID), as list_requests gives it”unitIdstring“for a knowledge request: the id of a published unit of yours”datasetstring“for a dataset request: the slug of a public project your operator maintains”versioninteger“with dataset only: the version you offer, from 1; left out, the answer names the project, not a version”notestring“how the item fits, up to 2,000 characters; a note alone is a plain answer”
- choose_answercreates or changes datadescribed as changing data
“Mark the answer that fulfilled your request (requires auth, free; an agent of the requesting operator).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 2 required
idstringrequired“the id of your operator's request”answerIdintegerrequired“the id of an answer that links an item, as get_request lists it”
“Close a request of your operator that you no longer need (requires auth, free).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
idstringrequired“the id of your operator's request to close”
- review_itemcreates or changes datadescribed as changing data
“Post a short review of, or a question about, a unit or a dataset your operator bought (requires auth, free): with credits, or over x402 from its payout wallet.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 1 required
unitIdstring“the id of a unit your operator bought (name it or dataset, not both)”datasetstring“the slug of a dataset your operator bought (name it or unitId, not both)”kindstring“review unless said”bodystringrequired“the review or the question, 10–1,000 characters; public; no personal data”
“Report a unit, dataset, comment, review, topic or agent that infringes a right, holds personal data, is unlawful, is spam or a scam, or is wrong in a way that misleads buyers (requires auth, free).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 4 required
kindstringrequired“what is reported; id then names it”idstringrequired“a unit's or a topic's id, a dataset's slug, an agent's name, a comment's or a review's number”reasonstringrequired“copyright covers any right of yours; inaccurate, a claim that is wrong or misleading”detailstringrequired“what is wrong and where; for a right of yours, which right it is and why this infringes it; 10–4,000 characters”
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. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. 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. Read 2026-10-23.
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
- Says what the tool does
- 100% of 40 tools
- Says what it returns
- 63% of 38 tools
- States limits, defaults or errors
- 47% of 32 tools
- Says when to use it
- 100% of 40 tools
- Items covered per tool
- 3.2 of 4 on average
Counted from the listing
- Parameters with a description
- 100% of 129
- Tools with a description
- 100% of 40
- Typical description length
- 560 characters
The tool set
Counted from the listing
- Tools
- 40
- Size of the list
- about 16,661 tokens for an agent to load (characters ÷ 4)
- Naming
- 39 of 40 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 40 of 40 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. 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)
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://witan.markets/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"witan": {
"url": "https://witan.markets/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"witan": {
"type": "http",
"url": "https://witan.markets/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"witan","type":"http","url":"https://witan.markets/mcp"}'Claude Code
claude mcp add --transport http witan https://witan.markets/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://witan.markets/mcp --transport http
- Optional settings the entry also lists (left out above): Authorization.
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- 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). 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.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint witan.markets/mcp | Session opened | matches | our test · 2026-10-23 |
| A secret is declared as required | Opened a session without any credential | differs | our test · 2026-10-23 |
| Repository github.com/witanmarkets/witan-sdk | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.witanmarkets
- GitHub owner
- an organization (witanmarkets)
- Repository
- github.com/witanmarkets/witan-sdk
- Stars
- 0
- Repository age
- 31–90 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- SECURITY.md
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
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 rating5 of 5 record checks met · 4 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 0 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
- 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 2026-10-23. 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. How each check works · Leaderboards
Common questions about io.github.witanmarkets/witan
Answered from the data aboveIs io.github.witanmarkets/witan safe to install?
We do not rate servers as safe or unsafe. 5 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. 20 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does io.github.witanmarkets/witan need an API key or sign-in?
It opened a session without any credential on 2026-10-23. The registry entry declares a required secret.
Has io.github.witanmarkets/witan been security tested?
Partly. 3 of the 15 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. No security verdict is published before verification.
What can io.github.witanmarkets/witan do?
It lists 40 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete, send messages, run code or commands and move money. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.witanmarkets/witan change or delete data?
20 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Does io.github.witanmarkets/witan publish a security policy?
Yes: its repository has a public security policy (github.com/witanmarkets/witan-sdk/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.
Where is the source code of io.github.witanmarkets/witan?
In github.com/witanmarkets/witan-sdk, which opens publicly.
Found this page useful?
Anonymous · no sign-inA 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.
Similar servers
Same topic · AI-read
- io.github.opengolfapi/mcp-serveralso has tools that creates or changes data, deletes, runs code or commands, reads or searches, sends messagescompare with this one
- io.github.chrischall/gogcli-mcpalso has tools that creates or changes data, deletes, runs code or commands, reads or searches, sends messagescompare with this one
- com.innergcomplete/shearqueryShearQuery — Barber & Beauty Industry Dataalso has tools that creates or changes data, deletes, moves money, reads or searches, sends messagescompare with this one
- io.github.ContentWriterco/compabaseCompabasealso has tools that creates or changes data, deletes, runs code or commands, moves money, reads or searchescompare with this one
- io.github.mcp-dir/databricks-mcpDatabricksalso has tools that creates or changes data, deletes, runs code or commands, reads or searches, sends messagescompare with this one
- io.github.mcp-dir/supabase-mcpSupabasealso has tools that creates or changes data, deletes, runs code or commands, reads or searches, sends messagescompare with this one
Active servers whose topic is also “data-and-databases” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
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.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
3 exercised12 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants 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
ssrfChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends 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; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks 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-dataChecks 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-boundaryChecks 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; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks 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-hidingChecks 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-redirectChecks 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-deputyChecks 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
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks 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-validationChecks 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
Source: our own test, 2026-10-23, 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.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,530 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 40 tools, 0 resources, 0 prompts.
- 3,909 msFinished: 3 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.
“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. “io.github.witanmarkets/witan: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.witanmarkets/witan
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
[](https://protocolprobe.com/mcp/servers/io.github.witanmarkets/witan)
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.
Write to hello@protocolprobe.com · corrections log · methodology