Atinamos Evidence

Read-only verification evidence for paid machine services and buyer policy checks.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
78%
Naming quality
90%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~593Tokens (tool definitions)
~536 BTypical response size
Minimal attention impact (0.46% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "evidence": {
      "url": "https://verify.atinamos.co.uk/mcp"
    }
  }
}

Remote endpoints

https://verify.atinamos.co.uk/mcpstreamable-http

What it can do

Tool inventory

Tools (6)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢lookup_assurance_evidence(endpoint, method)

Look up Atinamos Assurance evidence for an exact service endpoint. Uses the same DB-backed semantics as the human Assurance evidence lookup and GET /v1/assurance/evidence. Observations are returned even when no signed receipt exists; matching signed receipts are attached separately when available. It performs no service invocation or payment and returns no trust verdict.

Input Schema

{
  "type": "object",
  "properties": {
    "endpoint": {
      "title": "Endpoint",
      "type": "string"
    },
    "method": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Method"
    }
  },
  "required": [
    "endpoint"
  ],
  "title": "lookup_assurance_evidenceArguments"
}
🟢get_assurance_receipt(receipt_id)

Retrieve one complete signed Atinamos Assurance Evidence Receipt. The returned object is the signed receipt itself. Buyers can inspect the signed issuer key id, content hash, signature, timestamps, stages, assertions and limitations and independently verify the receipt.

Input Schema

{
  "type": "object",
  "properties": {
    "receipt_id": {
      "title": "Receipt Id",
      "type": "string"
    }
  },
  "required": [
    "receipt_id"
  ],
  "title": "get_assurance_receiptArguments"
}
⚪lookup_evidence(endpoint)

Look up Atinamos verification evidence for an exact service endpoint. Returns timestamped observations and evidence summaries. It does not return a universal trust or safety verdict.

Input Schema

{
  "type": "object",
  "properties": {
    "endpoint": {
      "title": "Endpoint",
      "type": "string"
    }
  },
  "required": [
    "endpoint"
  ],
  "title": "lookup_evidenceArguments"
}
⚪service_history(endpoint)

Return Atinamos's published observation history for one service route.

Input Schema

{
  "type": "object",
  "properties": {
    "endpoint": {
      "title": "Endpoint",
      "type": "string"
    }
  },
  "required": [
    "endpoint"
  ],
  "title": "service_historyArguments"
}
🟢search_services(query, limit)

Search services represented in the published Atinamos evidence corpus.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    },
    "limit": {
      "default": 20,
      "title": "Limit",
      "type": "integer"
    }
  },
  "required": [
    "query"
  ],
  "title": "search_servicesArguments"
}
⚪evaluate_policy(endpoint, policy)

Evaluate evidence against procurement rules supplied by the calling agent. The result is eligibility under the supplied rules, not an Atinamos buy/no-buy instruction. Supported policy keys currently include require_known, minimum_successful_fulfilments, maximum_failed_fulfilments, require_paid_evidence, max_evidence_age_days and max_price_usdc.

Input Schema

{
  "type": "object",
  "properties": {
    "endpoint": {
      "title": "Endpoint",
      "type": "string"
    },
    "policy": {
      "additionalProperties": true,
      "title": "Policy",
      "type": "object"
    }
  },
  "required": [
    "endpoint",
    "policy"
  ],
  "title": "evaluate_policyArguments"
}

Recommended Prompts

search_research
Search for information about [topic] using Atinamos Evidence
Expected tools: search_services
find_specific
Find [specific item] using Atinamos Evidence
Expected tools: search_services
retrieve_data
Get details about [item] from Atinamos Evidence
Expected tools: get_assurance_receipt
fetch_info
Fetch [information type] using Atinamos Evidence
Expected tools: get_assurance_receipt
research_workflow
Search for [topic], then get detailed information about the top results using Atinamos Evidence
Expected tools: search_servicesget_assurance_receipt

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded6 tools
verifiedversion not recorded6 tools