ProofMart is an MCP server published by io.github.ProofMart, hosted at proofmart.fly.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 3 tools, including verify_claim, check_agent_conduct, list_plans.
One-stop claim verification for AI agents: verdicts with confidence, evidence, signed receipts.
2 connections through 4 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs 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.
| Parameter | Type | Description |
|---|---|---|
| claim * | string | The factual claim to verify, e.g. 'The Eiffel Tower is in Paris.' |
{
"name": "verify_claim",
"title": "Verify a factual claim",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"claim"
],
"properties": {
"claim": {
"type": "string",
"minLength": 1,
"description": "The factual claim to verify, e.g. 'The Eiffel Tower is in Paris.'"
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"claim",
"verdict",
"confidence"
],
"properties": {
"claim": {
"type": "string"
},
"source": {
"enum": [
"ledger",
"checker",
"recheck"
],
"type": "string"
},
"account": {
"type": "object"
},
"receipt": {
"type": "object"
},
"verdict": {
"enum": [
"TRUE",
"FALSE",
"MIXED",
"UNVERIFIED"
],
"type": "string"
},
"evidence": {
"type": "array"
},
"confidence": {
"type": "integer",
"maximum": 100,
"minimum": 0
}
},
"additionalProperties": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| wallet | string | The agent's wallet address (0x…), as used to pay over x402. |
| identity | string | A full identity string: 'customer:<id>' or 'wallet:<address>'. |
| customer_id | integer | The agent's ProofMart customer id number. |
{
"name": "check_agent_conduct",
"title": "Pull an agent's conduct record (Conduct Feed)",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"wallet": {
"type": "string",
"description": "The agent's wallet address (0x…), as used to pay over x402."
},
"identity": {
"type": "string",
"description": "A full identity string: 'customer:<id>' or 'wallet:<address>'."
},
"customer_id": {
"type": "integer",
"description": "The agent's ProofMart customer id number."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"identity",
"standing"
],
"properties": {
"score": {
"type": [
"integer",
"null"
]
},
"evidence": {
"type": "object"
},
"identity": {
"type": "string"
},
"standing": {
"enum": [
"established",
"unproven",
"no_record"
],
"type": "string"
},
"components": {
"type": "object"
},
"attestation": {
"type": "object"
}
},
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}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.
No parameters.
{
"name": "list_plans",
"title": "List ProofMart plans",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}ProofMart verifies factual claims. Call the verify_claim tool with one claim and receive a verdict (TRUE / FALSE / MIXED / UNVERIFIED), a confidence score (0-100), the evidence behind it, and a signed receipt you can keep as proof of what was verified, when, and on what evidence. Checks are metered against the customer's ProofMart plan: send the customer key as the X-ProofMart-Key header (or Authorization: Bearer <key>). Without a key, a check can also be paid per call in USDC over the x402 protocol when that door is enabled (GET /health reports it): a keyless call is then answered 402 with payment requirements in the PAYMENT-REQUIRED header — pay and retry with the signed payment in the PAYMENT-SIGNATURE header. The check_agent_conduct tool pulls an agent's conduct record from the Conduct Feed (a separate business whose records are built from ProofMart check receipts): your OWN record is free with your customer key; another agent's record costs $0.05 in USDC over the same x402 door.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.