MCP servers › com.aurgus › aurgus
MCP server · registry snapshot 2026-11-01 · last tested 2026-11-01
com.aurgus/aurgus
by aurgus.com · domain (the registry's namespace rule)Website ↗
Governed rebate & revenue close (ASC 606/705/842): explain, ingest, compute, trace to source. — the publisher's description
Summary
com.aurgus/aurgus is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain aurgus.com. On 2026-11-01 ProtocolProbe connected to it in read-only mode and read its inventory: 38 tools, 0 resources and 1 prompt.
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- not applicable: The version the registry lists can be installed and is not withdrawn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
Operate this server? Correct a fact · README badge · Run the checks yourself
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
- Tools
- 38
- Last tested
- 2026-11-01
Tool list size
17,526 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (38 tools). Counted with Anthropic's token counter on 2026-11-01, from the tool list we read on 2026-11-01. Median across 25,738 counted servers: 2,858 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-01 (mcp.aurgus.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).
Observed fact
This server accepted a session without any credential and lists 5 tools whose name or declaration suggests they change data (set_cadence, defunct_agreement, edit_agreement_rates, edit_agreement, save_report). That is our reading of the names; we did not call them. Source: our connection, 2026-11-01.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-01
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.0, published 2026-11-01 (registry, as of the 2026-11-01 snapshot)
- First listed version
- 2026-11-01 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-11-01
- Package and repository
- checked 2026-11-01
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; 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 2026-10-31, listed on 2026-11-01 with version 1.0.0 (published 2026-11-01).
Source: the official MCP Registry list on 2026-10-31 and on 2026-11-01.
What it is
What does this server offer?
Observed inventoryNone of its 38 tools are described as changing anything. For 38 the reading was uncertain, so no mark is shown.
- begin
“Call this the moment the user greets Aurgus or wants to start — 'Aurgus, hi', 'hello', 'hey Aurgus', 'let's start', 'I want to run a close', 'where do I begin'.”
Publisher declares: read-only yes · destructive no
1 input
scenariostring“Optional: what the user wants to close, if they said (woven into the greeting).”
“Call this when the user asks for help or how to use Aurgus — 'Aurgus help', 'help', 'what can you do', 'how do I use this', 'show me the manual', 'what are the commands / trigger words'.”
Publisher declares: read-only yes · destructive no
Takes no inputs.
- release_notes
“What's new in Aurgus and how to stress-test it — call this for 'what changed', 'release notes', 'what's new', 'changelog', or if you're reviewing/pressure-testing the product.”
Publisher declares: read-only yes · destructive no
Takes no inputs.
- explainon 28 other servers
“State the governed US-GAAP treatment FOR A PAYMENT TYPE — a rebate, incentive, chargeback, or trade-spend payment — under ASC 606 (customer rebate / consideration payable to a customer / variable con…”
Publisher declares: read-only yes · destructive no
4 inputs
paymentstring“The nature of the payment.”buys_distinct_good_or_serviceboolean“True if the payment is in exchange for a distinct good or service the counterparty actually transfers (e.g.”fair_value_cap_usdnumber“Required only when buys_distinct_good_or_service is true: the fair value of that distinct good/service.”scenariostring“Optional free-text description of the user's scenario, for context.”
- request_real_run
“Get the link to run a real close on your OWN numbers — bring a rebate / SPA / deduction extract and get back audit-defensible accruals, full lineage, and an auditor-ready export, with nothing posted …”
Publisher declares: read-only no · destructive no
2 inputs
emailstring“Optional work email to set up access / follow up.”scenariostring“Optional short description of what the user wants to run.”
- aurgus
“THE one way to talk to Aurgus — the client's revenue-management controller.”
Publisher declares: read-only no · destructive no
7 inputs
messagestring“What the user said to Aurgus, verbatim.”engagement_idstring“The current engagement, once one is open.”entitystring“The client entity, when the user has named who they're closing for.”periodstring“The close period, when named (e.g.”programstring“The program being closed, when named (e.g.”who_certifiesstring“Who will certify the terms + mapping (name or email), when the user has named them — captured at open so the certifier is on the engagement from the start.”directionstring“Which side the client is on for a billback / chargeback / rebate: 'paying' (sell-side → ASC 606, reduces revenue) or 'receiving' (buy-side → ASC 705-20, reduce…”
- open_engagement
“Open a revenue-management engagement for a client.”
Publisher declares: read-only no · destructive no
6 inputs, 1 required
entitystringrequired“The client entity we're closing for (e.g.”periodstring“The close period (e.g.”programsarray“The rebate / SPA / billback program(s) in scope, if known.”sources_of_trutharray“The client's systems of record for this close.”who_certifiesstring“Who on the client side will certify the terms and mapping (name or email).”directionstring“Which side the client is on for a billback / chargeback / rebate: 'paying' (sell-side → ASC 606) or 'receiving' (buy-side → ASC 705-20).”
- engagement_status
“Report where an engagement stands — derived from the engagement file's real events, not a stored status.”
Publisher declares: read-only yes · destructive no
1 input
engagement_idstring“The engagement to report on.”
- request_documentson 1 other server
“Draft the PBC (prepared-by-client) document list for an engagement, FROM its agreement — the program decides which files the close needs (a sell-side rebate → the POS / sell-through extract; a buy-si…”
Publisher declares: read-only no · destructive no
1 input, 1 required
engagement_idstringrequired“The engagement to draft the PBC list for.”
- open_itemson 1 other server
“The engagement's open-items register — the things the close can't yet account for (a document not received, a term not found in the agreement, an unmatched figure).”
Publisher declares: read-only no · destructive no
5 inputs, 1 required
engagement_idstringrequired“The engagement whose register to act on.”actionstring“list (default), open a new item, or resolve one.”itemstring“For action=open: the open item's description.”ownerstring“For action=open: who owns resolving it.”item_idstring“For action=resolve: the id of the item being resolved.”
- receive_document
“Receive a client document into an engagement BY REFERENCE — a client-granted signed https link (or an upload handle), never the file's contents.”
Publisher declares: read-only no · destructive no
4 inputs, 2 required
engagement_idstringrequired“The engagement this document belongs to.”kindstringrequired“Which stream this is (pos = sell-through, claims = billbacks, credits = credit memos).”signed_urlstring“A client-granted signed https link to the file (e.g.”upload_handlestring“Alternatively, a handle to a file already uploaded to the client's tenant store.”
- compute_commission
“Compute a sales-commission engagement under ASC 340-40 (incremental cost to obtain a contract).”
Publisher declares: read-only no · destructive no
8 inputs, 4 required
engagement_idstringrequired“The commission engagement (opened via open_engagement, classified as a commission).”commission_usdnumberrequired“The commission — the incremental cost to obtain the contract.”benefit_monthsnumberrequired“The benefit period over which it amortizes, in months.”months_elapsednumberrequired“Months elapsed into the benefit period at this close.”expected_to_be_recoveredboolean“Whether the cost is expected to be recovered (340-40-25-1).”elect_practical_expedientboolean“Set true ONLY if the entity has ELECTED the ≤1-year practical expedient (340-40-25-4) to expense a commission that amortizes within a year.”contract_terminatedboolean“Set true if the underlying contract was TERMINATED early.”remaining_consideration_usdnumber“On a terminated contract, the consideration the entity still expects to receive (340-40-35-3(a)).”
Show 26 more tools
- compute_revenue_contract
“Run the full ASC 606 five-step recognition for a general revenue contract: identify the performance obligations (Step 2), allocate the transaction price by standalone selling price (Step 4), and reco…”
Publisher declares: read-only no · destructive no
3 inputs, 3 required
engagement_idstringrequired“The revenue-contract engagement (opened + classified as a general revenue contract).”transaction_price_usdnumberrequired“The contract's transaction price.”itemsarrayrequired“The promised items in the contract.”
- compute_lease
“Measure a lease under ASC 842 (v1: the lessee side — real estate and equipment).”
Publisher declares: read-only no · destructive no
11 inputs, 4 required
engagement_idstringrequired“The lease engagement (opened via open_engagement, classified as a lease).”term_periodsnumberrequired“The lease term as a number of periods.”periods_per_yearnumber“Periods per year: 12 monthly (default), 4 quarterly, 1 annual.”annual_discount_rate_pctnumberrequired“The CERTIFIED annual discount rate (%).”paymentsarrayrequired“The lease payment schedule.”incentives_usdnumber“Lease incentives received (e.g.”initial_direct_costs_usdnumber“Initial direct costs — added to the ROU asset.”prepaid_usdnumber“Payments made at or before commencement — added to the ROU asset.”payment_timingstring“Whether payments fall at period end (arrears, default) or start (advance).”classificationstring“The certified classification.”partystring“v1 is lessee-only; a lessor request is deferred to v2.”
- compute_trade_spend
“Split a trade-spend payment to a customer (co-op advertising, MDF, slotting, listing allowance) under ASC 606-10-32-26 / 705-20-25-2.”
Publisher declares: read-only yes · destructive no
3 inputs, 1 required
payment_usdnumberrequired“The trade-spend payment to the customer.”buys_distinct_good_or_serviceboolean“True if the customer transfers a distinct good/service (e.g.”fair_value_usdnumber“Fair value of that distinct good/service.”
- sign_close
“A principal signs the governed close for an engagement, by name, on the engagement file.”
Publisher declares: read-only no · destructive no
1 input, 1 required
engagement_idstringrequired“The engagement whose close is being signed.”
- export_workpapers
“Deliver the engagement workpapers — the certified figures and the open-items register on one page, from the hash-chained engagement file.”
Publisher declares: read-only yes · destructive no
1 input, 1 required
engagement_idstringrequired“The engagement to deliver workpapers for.”
- ingest_agreement
“Hand Aurgus your rebate agreement — PASTE its text, or DROP a PDF/scanned document (pass it as file_base64).”
Publisher declares: read-only no · destructive no
3 inputs
textstring“The agreement's text (paste the full agreement, or the rebate clauses).”file_base64string“A PDF or scanned-image agreement, base64-encoded.”filenamestring“The original filename (e.g.”
- compose_agreement
“Build a rebate/incentive agreement by talking it through — no document needed.”
Publisher declares: read-only no · destructive no
4 inputs, 1 required
descriptionstringrequired“Plain-language description of the program — who it's for, how it's measured and over what period, the rate/threshold/cap, the dates.”clarificationsarray“Answers to the follow-up questions from a previous turn, so the draft refines.”finalizeboolean“Set true ONLY after the terms have been reviewed and the follow-ups resolved.”proposalobject“Required when finalize=true: the EXACT drafted proposal returned by a prior (non-finalize) call, echoed back verbatim — so what is staged is exactly what was r…”
- ingeston 6 other servers
“Hand Aurgus one of your three rebate files (CSV) to read into your tenant: 'pos' (your POS / sell-through extract — what was earned), 'claims' (the claims you submitted), or 'credits' (credit memos /…”
Publisher declares: read-only no · destructive no
4 inputs, 2 required
csvstringrequired“The raw CSV content of your extract (header row + data rows).”kindstring“Which file this is: 'pos' (sales/POS extract — earned), 'claims' (claims submitted), or 'credits' (credit memos / vendor invoices received).”mappingobjectrequired“Map each of your column headers to an Aurgus field.”filenamestring“Optional original filename.”
- compute_close
“The RUN step (step 6) of an open engagement — work the governed, deterministic earned → settled → open accrual across the engagement's active agreements and certified data.”
Publisher declares: read-only no · destructive no
Takes no inputs.
- confirm_grouping
“Record the human's answer to a customer-grouping question Aurgus asked — a grouping compute_close PROPOSED ('GPG LLC resembles Global Procurement Group LLC', or 'these are the GPO's members'), OR a c…”
Publisher declares: read-only no · destructive no
3 inputs, 1 required
agreement_idstringrequired“The agreement whose customer scope this concerns — from the compute_close proposal or roster.”membersarray“Name(s) the user confirmed BELONG to this agreement (added as members), exactly as they appear in the data.”ended_membersarray“Member(s) that LEFT the group — their membership is ended as-of valid_to (not deleted; prior purchases stay attributed).”
- reporton 32 other servers
“The portfolio report — every active agreement on the tenant (or one, by id), with its earned / settled / open accrual, basis, status, and when it last calculated.”
Publisher declares: read-only yes · destructive no
2 inputs
agreement_idstring“Report on ONE agreement by id.”statusstring“Filter the list by lifecycle status.”
- set_cadence
“Set how often an agreement ACCRUES and SETTLES.”
Publisher declares: read-only no · destructive no
4 inputs, 1 required
agreement_idstringrequired“The agreement whose cadence to set.”accrual_cadencestring“How often to accrue.”settlement_cadencestring“How often it settles — when the rebate is actually paid out.”settlement_approver_emailstring“If someone must APPROVE each settlement before money moves, their email.”
- close_agreement
“Close an agreement for good — the terminal true-up at the END of its life (its term ended, or it's being wound down).”
Publisher declares: read-only no · destructive no
4 inputs, 1 required
agreement_idstringrequired“The agreement to close (terminal).”confirmboolean“Omit/false to DRY-RUN (preview the terminal true-up + freeze); true to post the Adjustment and close.”forceboolean“Administrative close flag, recorded on the audit trail (the true-up always resolves the open balance regardless).”reasonstring“Why it's being closed — recorded on the audit trail.”
- defunct_agreement
“Retire a WRONG agreement that has already accrued — reverse its postings, then archive it.”
Publisher declares: read-only no · destructive yes
2 inputs, 1 required
agreement_idstringrequired“The agreement to reverse & defunct.”confirmboolean“Omit/false to DRY-RUN (preview the reversal); true to actually reverse the postings and archive the agreement.”
- true_up
“True-up an agreement — AFTER a settlement, match the accrual account to what was ACTUALLY settled.”
Publisher declares: read-only no · destructive no
2 inputs, 1 required
agreement_idstringrequired“The agreement to true up.”confirmboolean“Omit/false to DRY-RUN (preview the Adjustment); true to post it.”
- edit_agreement_rates
“Change the RATES on a rate-routed (dimension-routed) agreement — a regime's flat rate, a tiered regime's own ladder, or the shared tier ladder.”
Publisher declares: read-only no · destructive no
4 inputs, 1 required
agreement_idstringrequired“The rate-routed agreement to edit.”regimesarray“Per-regime rate edits, keyed by the regime's key (from the dry-run list).”shared_tier_gridarray“The shared tier ladder (used by tiered regimes that tier on the whole book).”confirmboolean“Omit/false to DRY-RUN (list current rates or echo the change); true to apply and raise the gated Recalculate card.”
- edit_agreementon 1 other server
“Change an agreement's TERMS — its name, the counterparty (customer_name), the direction (payable_sell_side = you pay a rebate / receivable_buy_side = you earn one), the validity window (valid_from / …”
Publisher declares: read-only no · destructive no
8 inputs, 1 required
agreement_idstringrequired“The agreement to edit.”namestring“New agreement name.”customer_namestring“New counterparty / customer name.”directionstring“payable_sell_side (you pay the rebate) or receivable_buy_side (you earn it).”valid_fromstring“New validity start, YYYY-MM-DD (bare calendar date).”valid_tostring or null“New validity end, YYYY-MM-DD, or null for open-ended.”accrual_cadencestring“How often to accrue: realtime | daily | weekly | monthly | per_event.”settlement_cadencestring“How often it settles: weekly | semi_monthly | monthly | quarterly | semi_annual | annual | threshold | ad_hoc.”
- analyzeon 12 other servers
“Build a GOVERNED analytics report over the rebate data.”
Publisher declares: read-only yes · destructive no
4 inputs, 2 required
measurestringrequired“What to measure: accrued (earned) | settled (paid) | basis (transaction amount) | count (events).”group_bystringrequired“How to break it down: agreement | class (needs dimension_key) | month | quarter.”dimension_keystring“Required when group_by='class': the declared dimension to group by, e.g.”agreement_idstring“Optional — restrict the report to one agreement.”
- save_reporton 1 other server
“Save an analytics report for reuse.”
Publisher declares: read-only no · destructive no
5 inputs, 3 required
namestringrequired“A name to save this report under (e.g.”measurestringrequired“accrued | settled | basis | count.”group_bystringrequired“agreement | class (needs dimension_key) | month | quarter.”dimension_keystring“Required when group_by='class' — e.g.”agreement_idstring“Optional — restrict to one agreement.”
- list_reportson 22 other servers
“List the saved analytics reports on this tenant (name + what each measures).”
Publisher declares: read-only yes · destructive no
Takes no inputs.
- run_reporton 6 other servers
“Re-run a SAVED analytics report by name on current data — returns the grouped rows + total, governed and read-only exactly like `analyze`.”
Publisher declares: read-only yes · destructive no
1 input, 1 required
namestringrequired“The saved report's name (see `list_reports`).”
- recalculate
“Recalculate — re-run the deterministic engine over the POS data, dispatching every row against the agreement(s) so rows that just became eligible (e.g.”
Publisher declares: read-only no · destructive no
1 input
agreement_idstring“Recompute just this agreement.”
- connect_integrationon 1 other server
“Connect the client's ERP / POS / order system (or Zapier) to Aurgus by creating an API key for their account.”
Publisher declares: read-only no · destructive no
2 inputs
labelstring“Optional label.”confirmboolean“Omit/false to EXPLAIN what will be created and ask; true to actually create the key and return it once.”
- settleon 3 other servers
“Settle an agreement — post the PAYOUT.”
Publisher declares: read-only no · destructive no
2 inputs, 1 required
agreement_idstringrequired“The agreement to settle (pay out its open accrual).”confirmboolean“Omit/false to DRY-RUN (preview the payout + any blocking gate); true to post the Settlement event(s).”
- traceon 8 other servers
“Walk any accrued figure all the way back to where it came from — source row → eligibility → bucket → rate → rule → event chain — for a given transaction.”
Publisher declares: read-only yes · destructive no
2 inputs, 1 required
source_transaction_idstringrequired“The transaction id to trace.”agreement_idstring“Optional — limit to one agreement; otherwise all agreements that fired on the row.”
- exporton 17 other servers
“Put together the auditor-ready package for your tenant: the open accrual you can stand behind (earned → settled → open), where margin is leaking versus what's sitting outside any program, and sample …”
Publisher declares: read-only yes · destructive no
Takes no inputs.
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 2026-11-01.
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
- 100% of 115
- Tools with a description
- 100% of 38
- Typical description length
- 573 characters
The tool set
Counted from the listing
- Tools
- 38
- Size of the list
- about 12,659 tokens for an agent to load (characters ÷ 4)
- Naming
- 27 of 38 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 38 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)
We connected to this URL on 2026-11-01 (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://mcp.aurgus.com/api/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"aurgus": {
"url": "https://mcp.aurgus.com/api/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"aurgus": {
"type": "http",
"url": "https://mcp.aurgus.com/api/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"aurgus","type":"http","url":"https://mcp.aurgus.com/api/mcp"}'Claude Code
claude mcp add --transport http aurgus https://mcp.aurgus.com/api/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"aurgus": {
"type": "streamableHttp",
"url": "https://mcp.aurgus.com/api/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"aurgus": {
"httpUrl": "https://mcp.aurgus.com/api/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.aurgus] url = "https://mcp.aurgus.com/api/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"aurgus": {
"url": "https://mcp.aurgus.com/api/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://mcp.aurgus.com/api/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.
Does the registry listing match what we found?
Feature #6The 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 says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint mcp.aurgus.com/api/mcp | Session opened | matches | our test · 2026-11-01 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-01 |
Choosing
Record checks
Public records · not a safety rating1 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 registry entry gives no repository link.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 2026-11-01. 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.aurgus/aurgus
Answered from the data aboveWho publishes com.aurgus/aurgus?
The registry ties the namespace com.aurgus to the domain aurgus.com; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does com.aurgus/aurgus need an API key or sign-in?
It opened a session without any credential on 2026-11-01. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.aurgus/aurgus been security tested?
Partly. 5 of the 16 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.
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.
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: exercised
- Fake assistant turns: exercised
- 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
5 exercised11 not run (reason given)2 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 5 of the 16 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 - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised - 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.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 - 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
- 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, 2026-11-01, 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
- 803 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 38 tools, 0 resources, 1 prompt.
- 4,318 msFinished: 5 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. “com.aurgus/aurgus: MCP server record.” Data checked 2026-11-01. https://protocolprobe.com/mcp/servers/com.aurgus/aurgus
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/com.aurgus/aurgus)
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