{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_mssuxt9d6uqn","handle":"mcp-evaluation-server","url":"https://wellknown.network/agents/mcp-evaluation-server","links":{"self":"https://wellknown.network/agents/mcp-evaluation-server/record.json","html":"https://wellknown.network/agents/mcp-evaluation-server","markdown":"https://wellknown.network/agents/mcp-evaluation-server/record.md","api":"https://wellknown.network/api/v1/agents/mcp-evaluation-server","status":"https://wellknown.network/api/v1/agents/mcp-evaluation-server/status","claim":"https://wellknown.network/agents/mcp-evaluation-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-evaluation-server/claim.json","badge":"https://wellknown.network/agents/mcp-evaluation-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-evaluation-server/history","tools":"https://wellknown.network/api/v1/agents/mcp-evaluation-server/tools"},"ard":{"identifier":"urn:air::server:mcp-evaluation-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-evaluation-server","summary":"MCP工具评估助手服务器 - 优化Cherry Studio兼容性","description":"# MCP Evaluation Server\n一个基于FastMCP的MCP工具评估服务器，提供工具搜索、评估和分类功能。\n\n## 功能特性\n\n- 🔍 **工具搜索**：支持关键词、分类、评分等多维度搜索\n- 🏆 **热门工具**：提供各类评分的热门工具排行榜\n- 📊 **详细评估**：包含他山评分、实用性评分等多维度评估\n- 📂 **分类管理**：按工具分类进行统计和展示\n- 🏥 **健康检查**：实时监控服务状态\n- 🚀 **高性能**：基于FastMCP框架，响应迅速\n\n## 安装\n\n### 从PyPI安装\n\n```bash\npip install mcp-evaluation-server\n```\n\n### 使用uv安装\n\n```bash\nuv add mcp-evaluation-server\n```\n\n### 使用uvx运行（推荐）\n\n无需安装，直接运行：\n\n```bash\nuvx mcp-evaluation-server\n```\n\n## 作为MCP服务器使用\n\n本服务器可以作为MCP（Model Context Protocol）服务器在支持的AI客户端中使用，如Cursor、Cherry Studio等。\n\n### 在Cursor中使用\n\n1. **打开Cursor设置**\n   - 按下 `Ctrl+,` (Windows/Linux) 或 `Cmd+,` (Mac)\n   - 进入 `Extensions` → `MCP`\n\n2. **添加MCP服务器配置**\n   在 `mcp.json` 配置文件中添加：\n\n   ```json\n   {\n     \"mcpServers\": {\n       \"mcp-evaluation\": {\n         \"command\": \"uvx\",\n         \"args\": [\"mcp-evaluation-server\"]\n       }\n     }\n   }\n   ```\n\n3. **重启Cursor**\n   - 完成配置后重启Cursor使设置生效\n\n4. **使用功能**\n   - 重启后，您可以在对话中直接询问关于MCP工具的问题\n   - 例如：\"搜索GitHub相关的MCP工具\"\n   - 或：\"获取评分最高的MCP工具\"\n\n### 在Cherry Studio中使用\n\n1. **打开Cherry Studio**\n   - 启动Cherry Studio应用\n\n2. **进入MCP设置**\n   - 点击设置图标\n   - 找到MCP服务器配置选项\n\n3. **添加服务器**\n   添加以下配置：\n   - **服务器名称**: `mcp-evaluation`\n   - **命令**: `uvx`\n   - **参数**: `mcp-evaluation-server`\n\n4. **启用服务器**\n   - 启用刚添加的MCP服务器\n   - 重启Cherry Studio\n\n5. **开始使用**\n   - 在对话中可以直接使用MCP工具评估功能\n   - 询问工具推荐、评分等信息\n\n## 程序化使用\n\n### Python API调用\n\n```python\nimport asyncio\nfrom mcp_evaluation_server import (\n    search_mcp_tools,\n    get_top_tools,\n    get_tool_evaluation\n)\n\nasync def main():\n    # 搜索工具\n    results = await search_mcp_tools(query=\"github\", limit=10)\n    print(f\"找到 {len(results['tools'])} 个工具\")\n    \n    # 获取热门工具\n    top_tools = await get_top_tools(sort_by=\"tashan_score\", limit=5)\n    print(f\"热门工具: {[tool['name'] for tool in top_tools['tools']]}\")\n    \n    # 获取工具评估\n    evaluation = await get_tool_evaluation(\"github-mcp-server\")\n    print(f\"评估分数: {evaluation['evaluation']['comprehensive_score']}\")\n\nasyncio.run(main())\n```\n\n### 直接启动服务器\n\n```bash\n# 使用uvx启动MCP服务器（推荐）\nuvx mcp-ev…","publisher":{"name":"gqy20","url":null},"homepage":"https://github.com/gqy20/mcp-evaluation-server","repository":"https://github.com/gqy20/mcp-evaluation-server","version":"0.3.2","license":"MIT","protocols":["mcp"],"tags":["mcp","evaluation","tools","server"],"pricing":null,"endpoints":[{"url":"pypi:mcp-evaluation-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"declared"}],"categories":["ai"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-evaluation-server","registry":"pypi","observedAt":"2026-10-28T11:27:09.973Z","publishedAt":"2025-09-24T07:18:36.559315Z","latestVersion":"0.3.2"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-evaluation-server","url":"https://pypi.org/project/mcp-evaluation-server/","firstSeenAt":"2026-09-10T01:20:29.581Z","fetchedAt":"2026-10-28T11:25:18.428Z","normalizedAt":"2026-10-28T11:25:18.428Z"}]},"firstSeenAt":"2026-09-10T01:20:29.581Z","updatedAt":"2026-10-28T11:27:09.973Z"}