MCP MeasureMCP Measure

index observed

Matchmaking rating for agent selection

Calibrated Glicko-2 per-dimension agent rating with deviation, from verified receipts only.

Should I use this

Quality & Safety

B
Description quality
73%
Schema completeness
70%
Naming quality
87%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (2)

  • LOWTool 'rank_agents' description lacks action verbin rank_agents
  • LOWTool 'ingest_receipt' description lacks action verbin ingest_receipt

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~166Tokens (tool definitions)
~394 BTypical response size
Minimal attention impact (0.13% 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": {
    "matchmaking-rating-for-agent-selection": {
      "url": "https://textforagents.com/products/matchmaking-rating-for-agent-selection/mcp"
    }
  }
}

Remote endpoints

https://textforagents.com/products/matchmaking-rating-for-agent-selection/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢query_rating(agent, dimension, task_rating)

Pre-delegation query $0.01 (trial applies)

Input Schema

{
  "type": "object",
  "properties": {
    "agent": {
      "type": "string"
    },
    "dimension": {
      "type": "string"
    },
    "task_rating": {
      "type": "number"
    }
  }
}
⚪rank_agents(dimension, candidates, mode, consequence, prov_budget, ...)

Rank candidates $0.01 (trial applies)

Input Schema

{
  "type": "object",
  "properties": {
    "dimension": {
      "type": "string"
    },
    "candidates": {
      "type": "array"
    },
    "mode": {
      "type": "string"
    },
    "consequence": {
      "type": "string"
    },
    "prov_budget": {
      "type": "integer"
    },
    "task_rating": {
      "type": "number"
    }
  }
}
⚪ingest_receipt(receipt)

Ingest verified receipt (verifier-signed)

Input Schema

{
  "type": "object",
  "properties": {
    "receipt": {
      "type": "object"
    }
  }
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools