mcp-judge

Automatically evaluates other MCP servers (conformance, docs, latency) and returns an objective 0–100 quality score with an A–F grade — no human, no LLM…

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • List Criteria: FREE, no payment required. Returns the exact criteria MCP Judge uses to score an MCP server: each criterion, its weight out of 100, and the A-F grade scale. Call this to understand how
  • Evaluate Mcp: FREE during beta (will become PAID $0.05 via x402). Evaluates another MCP server and returns an objective quality report so an agent can decide whether to trust and integrate it. Set 'ur

What data it sees

Do you need an account

No: the server works without sign-in

Automatically evaluates other MCP servers (conformance, docs, latency) and returns an objective 0–100 quality score with an A–F grade — no human, no LLM opinion.

How to connect

How to connect mcp-judge to Claude

The server address to paste into Claude settings:

https://mcp-judge--giachi85it.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect mcp-judge to ChatGPT

The server address to paste into ChatGPT settings:

https://mcp-judge--giachi85it.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect mcp-judge to Cursor

The server address to paste into Cursor settings:

https://mcp-judge--giachi85it.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (2)

Raw names from tools/list. Only developers need these.

list_criteriaFREE, no payment required. Returns the exact criteria MCP Judge uses to score an MCP server: each criterion, its weight out of 100, and the A-F grade scale. Call this to understand how evaluate_mcp works before paying for it. The evaluation is fully objective and automated — no human reviewer and no AI opinion. Takes no parameters.
evaluate_mcpFREE during beta (will become PAID $0.05 via x402). Evaluates another MCP server and returns an objective quality report so an agent can decide whether to trust and integrate it. Set 'url' (required) to the target's MCP endpoint (Streamable HTTP), e.g. https://host/mcp. MCP Judge connects, runs the 'initialize' handshake and 'tools/list', measures latency, checks how well tools and parameters are documented, and safely probes free tools — it never pays to test paid tools, it only verifies they are cleanly declared. Returns a structured report: reachability, protocol and serverInfo, per-tool documentation coverage, latency, a functional probe, a 0-100 score with letter grade and breakdown, and a plain-language summary. Objective checks only — no human and no LLM opinion.