Integrates with AntV charting library through mcp-server-chart to create interactive data visualizations and dashboards from analyzed data
Enables AI-powered data analysis and business intelligence capabilities using pandas DataFrames, including statistical analysis, data manipulation, and automated report generation
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ChatBI MCP Serveranalyze sales trends for the last quarter and create a summary report"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.txtRelated MCP server: R Econometrics MCP Server
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:

This server cannot be installed
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.