ProofMart
One-stop claim verification for AI agents: verdicts with confidence, evidence, signed receipts.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"proofmart": {
"url": "https://proofmart.fly.dev/mcp"
}
}
}Remote-Endpunkte
https://proofmart.fly.dev/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (3)
🟡verify_claim(claim)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"claim": {
"type": "string",
"description": "The factual claim to verify, e.g. 'The Eiffel Tower is in Paris.'",
"minLength": 1
}
},
"required": [
"claim"
],
"additionalProperties": false
}Ausgabe-Schema
{
"type": "object",
"properties": {
"claim": {
"type": "string"
},
"verdict": {
"type": "string",
"enum": [
"TRUE",
"FALSE",
"MIXED",
"UNVERIFIED"
]
},
"confidence": {
"type": "integer",
"minimum": 0,
"maximum": 100
},
"evidence": {
"type": "array"
},
"source": {
"type": "string",
"enum": [
"ledger",
"checker",
"recheck"
]
},
"receipt": {
"type": "object"
},
"account": {
"type": "object"
}
},
"required": [
"claim",
"verdict",
"confidence"
],
"additionalProperties": true
}🟢check_agent_conduct(customer_id, wallet, identity)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"customer_id": {
"type": "integer",
"description": "The agent's ProofMart customer id number."
},
"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>'."
}
},
"additionalProperties": false
}Ausgabe-Schema
{
"type": "object",
"properties": {
"identity": {
"type": "string"
},
"score": {
"type": [
"integer",
"null"
]
},
"standing": {
"type": "string",
"enum": [
"established",
"unproven",
"no_record"
]
},
"components": {
"type": "object"
},
"evidence": {
"type": "object"
},
"attestation": {
"type": "object"
}
},
"required": [
"identity",
"standing"
],
"additionalProperties": true
}🟢list_plans
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.
Eingabe-Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}Community
Nachweis