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 opinion.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

模型生成摘要（rules/v1 · 2026-09-27 16:42）：Automatically evaluates other MCP servers (conformance, docs, latency) and returns an objective 0–100 quality score with…
这是模型对公开材料的总结，不是官方声明，请以原链内容为准。

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://mcp-judge--giachi85it.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "mcp-judge": {
      "url": "https://mcp-judge--giachi85it.run.tools"
    }
  }
}

能力清单

工具

说明

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 works before paying for it. The evaluation is fully objective and automated — no human reviewer and no AI opinion. Takes no parameters.

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 '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.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。