MCP MeasureMCP Measure

index observed

Agent Evidence API

MCP-native web evidence and claim verification: cited, source-grounded evidence for AI agents.

Quality & Safety

B
Description quality
100%
Schema completeness
65%
Naming quality
80%
Poisoning risk
80%
Permission match
100%
Protocol compliance
100%

Findings (2)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains suspicious base64-like encoded stringin research_evidence

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~417Tokens (tool definitions)
~1.4 KBTypical response size
Minimal attention impact (0.33% 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.

Rate this Server

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "agent-evidence-api": {
      "url": "https://agent-evidence-api.taher-h-alhaddad.workers.dev/mcp"
    }
  }
}

Remote endpoints

https://agent-evidence-api.taher-h-alhaddad.workers.dev/mcpstreamable-http
https://agent-evidence-api.thx93workersdev.workers.dev/mcpstreamable-http
https://agent-evidence-api.thx93.workers.dev/mcpstreamable-http

Tool inventory

Tools (2)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢research_evidence(question, urls, max_sources, language, mode)

Fetch public web sources and return structured, cited web evidence for a question or claim. Use this for source verification, claim verification, evidence extraction, and source-grounded research, or to compare sources. Returns source URLs, retrieval timestamps, short evidence excerpts, publisher and document metadata, and an explicit supported/contradicted/mixed/inconclusive assessment. Fresh web evidence is retrieved per request unless served from a bounded cache, and each source reports its actual retrieval time. Every excerpt returned is cited evidence tied to its source URL.

Input Schema

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2000,
      "description": "The question or claim to gather web evidence for."
    },
    "urls": {
      "description": "Candidate public source URLs to retrieve and cite. Version 0.1.0 requires at least one such URL.",
      "maxItems": 25,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "max_sources": {
      "description": "Cap on the number of sources processed.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 25
    },
    "language": {
      "description": "Preferred evidence language: \"auto\" or a BCP-47 tag such as \"en\".",
      "type": "string",
      "minLength": 1,
      "maxLength": 35
    },
    "mode": {
      "description": "Reserved input. Only \"evidence\" is supported in version 0.1.0.",
      "type": "string",
      "enum": [
        "evidence"
      ]
    }
  },
  "required": [
    "question"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢health

Check that the Agent Evidence API MCP server is reachable and report which service version is running. Free to call, takes no arguments or payment. Returns only {status, service, version} and exposes no secrets or infrastructure detail.

Input Schema

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Recent observations

verifiedversion not recorded2 tools