{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_mscptc7qqcxn","handle":"bachai-data-analysis-mcp","url":"https://wellknown.network/agents/bachai-data-analysis-mcp","links":{"self":"https://wellknown.network/agents/bachai-data-analysis-mcp/record.json","html":"https://wellknown.network/agents/bachai-data-analysis-mcp","markdown":"https://wellknown.network/agents/bachai-data-analysis-mcp/record.md","api":"https://wellknown.network/api/v1/agents/bachai-data-analysis-mcp","status":"https://wellknown.network/api/v1/agents/bachai-data-analysis-mcp/status","claim":"https://wellknown.network/agents/bachai-data-analysis-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/bachai-data-analysis-mcp/claim.json","badge":"https://wellknown.network/agents/bachai-data-analysis-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/bachai-data-analysis-mcp/history","tools":"https://wellknown.network/api/v1/agents/bachai-data-analysis-mcp/tools"},"ard":{"identifier":"urn:air::server:bachai-data-analysis-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"bachai-data-analysis-mcp","summary":"Data Analysis MCP Server - Model Context Protocol server for data analysis (stdio and SSE modes)","description":"# Data Analysis MCP (Python)\n\n一个基于 Model Context Protocol 的数据分析服务器，使用 Python 开发，支持 **SSE (Server-Sent Events)** 传输模式。\n\n## 功能特性\n\n- 📊 数据统计分析（均值、中位数、标准差等）\n- 📈 数据可视化（生成图表）\n- 🔍 数据探索（查看数据摘要、缺失值等）\n- 📉 趋势分析\n- 📋 支持 CSV、Excel、JSON 等格式\n- 🌐 基于 HTTP/SSE 的远程访问\n- 🚀 RESTful API 接口\n\n## 技术栈\n\n- Python 3.8+\n- FastAPI - 现代化 Web 框架\n- SSE-Starlette - Server-Sent Events 支持\n- Uvicorn - ASGI 服务器\n- pandas - 数据分析\n- numpy - 数值计算\n- matplotlib - 数据可视化\n- seaborn - 统计图表\n\n## 快速开始\n\n### 安装依赖\n\n```bash\npip install -r requirements.txt\n```\n\n### 运行服务器\n\n#### 方式 1: stdio 模式（用于 supergateway/Claude Desktop）\n\n```bash\n# 使用 uvx (推荐)\nuvx bachai-data-analysis-mcp\n\n# 或使用 pip 安装后运行\npip install bachai-data-analysis-mcp\nbachai-data-analysis-mcp\n```\n\nstdio 模式通过标准输入输出进行通信，适合与 supergateway 或 Claude Desktop 集成。\n\n#### 方式 2: SSE 模式（独立 HTTP 服务器）\n\n```bash\n# 直接运行\npython main.py\n\n# 或使用命令\nbachai-data-analysis-mcp-sse\n```\n\n服务器将在 `http://localhost:8000` 启动。\n\n### 访问 API 文档\n\n启动后访问：\n- **Swagger UI**: http://localhost:8000/docs\n- **ReDoc**: http://localhost:8000/redoc\n\n## API 端点\n\n### 1. 根端点\n```\nGET http://localhost:8000/\n```\n返回服务器信息和可用端点\n\n### 2. SSE 连接端点\n```\nGET http://localhost:8000/sse\n```\n建立 Server-Sent Events 连接，接收服务器推送的消息\n\n### 3. 消息处理端点\n```\nPOST http://localhost:8000/messages\nContent-Type: application/json\n```\n发送 MCP JSON-RPC 请求\n\n#### 示例请求：\n\n**初始化**\n```json\n{\n  \"jsonrpc\": \"2.0\",\n  \"id\": 1,\n  \"method\": \"initialize\",\n  \"params\": {}\n}\n```\n\n**列出工具**\n```json\n{\n  \"jsonrpc\": \"2.0\",\n  \"id\": 2,\n  \"method\": \"tools/list\",\n  \"params\": {}\n}\n```\n\n**调用工具**\n```json\n{\n  \"jsonrpc\": \"2.0\",\n  \"id\": 3,\n  \"method\": \"tools/call\",\n  \"params\": {\n    \"name\": \"load_data\",\n    \"arguments\": {\n      \"filepath\": \"data.csv\",\n      \"dataset_name\": \"my_data\"\n    }\n  }\n}\n```\n\n## MCP 工具列表\n\n### 1. load-data\n加载数据文件\n- 支持 CSV、Excel、JSON 格式\n\n### 2. describe-data\n获取数据摘要统计\n- 行列数\n- 数据类型\n- 缺失值统计\n- 基本统计量\n\n### 3. analyze-column\n分析特定列的数据\n- 唯一值数量\n- 频率分布\n- 数值统计\n\n### 4. correlation-analysis\n相关性分析\n- 计算变量间相关系数\n- 生成相关性矩阵\n\n### 5. list-datasets\n列出已加载的数据集\n- 显示所有数据集\n- 查看数据集基本信息\n\n…","publisher":{"name":"BACH Studio","url":null},"homepage":"https://github.com/BACH-AI-Tools/data-analysis-mcp","repository":"https://github.com/BACH-AI-Tools/data-analysis-mcp","version":"1.1.6","license":"MIT","protocols":["mcp"],"tags":["mcp","data-analysis","pandas","machine-learning","sse"],"pricing":null,"endpoints":[{"url":"pypi:bachai-data-analysis-mcp","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":"documents.spreadsheets","name":"Spreadsheets","confidence":0.733,"provenance":"derived"}],"categories":["documents"],"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":"bachai-data-analysis-mcp","registry":"pypi","observedAt":"2026-10-27T20:23:56.819Z","publishedAt":"2025-11-07T02:25:10.685320Z","latestVersion":"1.1.6"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"bachai-data-analysis-mcp","url":"https://pypi.org/project/bachai-data-analysis-mcp/","firstSeenAt":"2026-09-09T10:26:24.930Z","fetchedAt":"2026-10-27T20:22:47.081Z","normalizedAt":"2026-10-27T20:22:47.081Z"}]},"firstSeenAt":"2026-09-09T10:26:24.930Z","updatedAt":"2026-10-27T20:23:56.819Z"}