chatbi-mcp-server
使用LLM生成代码来对Excel进行分析的MCP Server
Documentation
ChatBI MCP Server
准备环境
配置LLM API Key
cp .env.example .env编辑`.env`文件,填写LLM信息,要生成代码,建议填写相对比较强的模型,比如GLM 4.5、Qwen-235B-A22B、Kimi K2等,至少Qwen3-32B,规模再小的生成代码质量会比较差,分析效果差。
安装依赖
uv venv .venv --python=3.11
source .venv/bin/activate
uv pip install -r requirements.txt运行服务
cd src
python pandas_mcp_server.py使用
配置ChatBI MCP Server
使用任意支持MCP Server的客户端,比如Cherry Studio,配置如下:

其中验证信息,在`config.yaml`中,可以自行修改。默认值为`eyJzdWIiOiAidXNlcjEyMyIsICJpYXQiOiAxNzUxODA5ODIwLCAiZXhwIjogMTc1MTgxMzQyMH0`。
> 注意:超时时间设置长一点,因为涉及LLM生成代码、如果出错还需要改错
添加完成后,点击“保存”,然后点击又上方的开启选项,切换到“工具”标签页:
如果能正常列出工具,说明配置正确。

使用ChatBI MCP Server
常规统计
使用时,记得开启这个MCP Server:


可视化
结合mcp-server-chart使用

综合运用
通过指令,自动化数据分析:
生成数据分析计划:

开始分析:

结果报告:


生成的看板:

Frequently asked questions
What is chatbi-mcp-server?
chatbi-mcp-server is 使用LLM生成代码来对Excel进行分析的MCP Server
How do I install chatbi-mcp-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is chatbi-mcp-server open source?
Yes — it is hosted on GitHub at https://github.com/steven-luo/chatbi-mcp-server and has 12 stars.
Related MCP tools
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to
🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。 for the Model Context Protocol. Enhance AI assistants with po
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP