MCP MeasureMCP Measure

index observed

AgentWatchr

Read-only agent identity index with provenance, historical evidence and explained coverage.

Should I use this

Quality & Safety

B
Description quality
85%
Schema completeness
63%
Naming quality
100%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~186Tokens (tool definitions)
~275 BTypical response size
Minimal attention impact (0.15% 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-index": {
      "url": "https://agentwatchr.com/mcp"
    }
  }
}

Remote endpoints

https://agentwatchr.com/mcpstreamable-http

What it can do

Tool inventory

Tools (4)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢search_agents(query, source)

Search observed source identities, not verified real-world agents.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "source": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
🟢get_agent(id)

Read profile, evidence and explained Evidence Score.

Input Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢get_stats

Read evidence and coverage distributions.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_insights(section)

Read bounded FACT / INTERPRETATION / CONFIDENCE network analyses.

Input Schema

{
  "type": "object",
  "properties": {
    "section": {
      "type": "string"
    }
  },
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded4 tools