ProofMart MCP server
io.github.ProofMart/proofmartProofMartstreamable-httpv0.12.0Scanned
One-stop claim verification for AI agents: verdicts with confidence, evidence, signed receipts.
3 tools: 2 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the ProofMart MCP server can do
The ProofMart MCP server is published by the GitHub account ProofMart. It has 3 tools. It can create or change data (2 tools: verify_claim and check_agent_conduct), but cannot delete data. 1 tool only reads.
1 tool brings in text other people can write (verify_claim).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 0.12.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Changes things 2Claude Code: ask
check_agent_conductAsk the Conduct Feed — a separate business from ProofMart, whose records are built from ProofMart check receipts — how an agent has behaved: a 0-100 conduct score with its componen…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Ask the Conduct Feed — a separate business from ProofMart, whose records are built from ProofMart check receipts — how an agent has behaved: a 0-100 conduct score with its component scores, the evidence mix behind it (event counts by tier, record span, settled payments), contested markings, and a signed attestation. Identify the agent by customer_id (a ProofMart customer number) or by wallet (its x402 payer address). Your OWN record is free when you send your customer key; pulling another agent's record costs $0.05, paid in USDC over x402: a call that needs payment is answered 402 with payment requirements in the PAYMENT-REQUIRED header — pay and retry with the signed payment in the PAYMENT-SIGNATURE header. An agent with no history answers standing 'no_record' — never a fabricated score. Full method: GET /conduct/methodology.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
verify_claimSubmit one factual claim to ProofMart and get back a verdict (TRUE / FALSE / MIXED / UNVERIFIED), a confidence score (0-100), the evidence behind the verdict, and a signed receipt.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Submit one factual claim to ProofMart and get back a verdict (TRUE / FALSE / MIXED / UNVERIFIED), a confidence score (0-100), the evidence behind the verdict, and a signed receipt. Verdicts are remembered in ProofMart's Ledger: a claim that was already checked and is still fresh is answered instantly from memory (the result's 'source' field says 'ledger'; fresh research says 'checker'). Compound claims are split into individual facts automatically. One call = one metered check against the customer's plan.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 1Show 1 read-only tool
list_plansThe ProofMart menu: each plan's monthly check bundle and draft price.No findings
Why it is in this group
- The name "list_plans" says "list": a word for reading.
Description, as the server wrote it The ProofMart menu: each plan's monthly check bundle and draft price. Free to call — no key needed, nothing metered. Useful when an owner asks what subscribing would get them.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 17, 2026, 15:23 UTC, unchanged since Nov 3, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://proofmart.fly.dev/mcp: tools/list returned 3 tools to an anonymous client, including verify_claim (write), check_agent_conduct (write)
Posture changes
- Nov 3, 2026
- Tools that change things, listed without credentials: 1 to 2
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 2.View diff
- Tools that change things, listed without credentials: 1 to 2
Tools1 added.+1 addedView diff
- Added:check_agent_conductChanges things
Install
Pinned to version 0.12.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http proofmart https://proofmart.fly.dev/mcp --header 'X-ProofMart-Key: <your-x-proofmart-key>'claude mcp add --transport http proofmart https://proofmart.fly.dev/mcp --header 'X-ProofMart-Key: <your-x-proofmart-key>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__proofmart__list_plans"
],
"ask": [
"mcp__proofmart__verify_claim",
"mcp__proofmart__check_agent_conduct"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as proofmart. Review it before you use it.
Capability tags behind 1 rule
- mcp__proofmart__verify_claim untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.ProofMart/proofmart/verify?hash=b4435abfbfa0b320d830113a521fd7d0fd237ca858e802680059b4fc311aa59c" | jq -e '.changed == false'Pinned hash b4435abfbfa0, from Nov 10, 2026, 15:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.ProofMart/proofmart/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.ProofMart/proofmart)Source: MCP Registry. Synced Oct 29, 2026, 07:17 UTC.
ProofMart MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ProofMart MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ProofMart MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ProofMart MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the ProofMart MCP server have?
- 3 tools: 2 write, 1 read. verify_claim, check_agent_conduct and list_plans.
Does the ProofMart MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ProofMart MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ProofMart MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Oct 29, 2026. Every change is on this page and in its Atom feed.