MCPgee
MCPgee
MCPgeeMCPgee

ChatBI

v1.0.0•Analytics•stable

使用LLM生成代码来对Excel进行分析的MCP Server

chatbimcpai-integration
Share:
15
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is ChatBI?

ChatBI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 使用llm生成代码来对excel进行分析的mcp server

使用LLM生成代码来对Excel进行分析的MCP Server

This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 使用LLM生成代码来对Excel进行分析的MCP Server

Use Cases

Generate code to analyze Excel spreadsheets with LLMs.
Perform data analysis through natural language queries.
Steven-Luo

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedApr 2, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx chatbi

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use ChatBI

ChatBI MCP Server is a Python-based MCP server that uses large language models to generate and execute data analysis code against Excel and tabular data files. It translates natural language questions into Python/Pandas code, runs the analysis, and can produce charts and dashboards via integration with an mcp-server-chart companion. Data analysts and business intelligence users who want to query spreadsheets conversationally — without writing code themselves — can drop this server into any MCP-compatible AI client to get instant, reproducible analyses.

Prerequisites

  • Python 3.11 (exactly, as specified in the project) with uv package manager installed
  • An LLM API key for one of the supported models: GLM 4.5, Qwen-235B-A22B, Kimi K2, or Qwen3-32B (minimum)
  • An MCP-compatible client such as Cherry Studio or Claude Desktop
1

Clone the repository

Clone the ChatBI MCP server repository to your local machine.

git clone https://github.com/Steven-Luo/chatbi-mcp-server.git
cd chatbi-mcp-server
2

Create a Python 3.11 virtual environment and install dependencies

Use uv to create a virtual environment pinned to Python 3.11 and install all requirements.

uv venv .venv --python=3.11
source .venv/bin/activate
uv pip install -r requirements.txt
3

Configure your LLM API credentials

Copy the example environment file and fill in your LLM API key and endpoint. The server supports GLM 4.5, Qwen, and Kimi K2 models — smaller models will produce lower-quality code analysis.

cp .env.example .env
# Edit .env and set your API key and model endpoint
4

Configure authentication token in config.yaml (optional)

The server uses a JWT-style auth token defined in config.yaml. The default token works for local use; replace it with a custom value if you expose the server beyond localhost.

5

Start the MCP server

Launch the Pandas MCP server from the src directory. It listens for MCP client connections over stdio by default.

cd src
python pandas_mcp_server.py
6

Add the server to your MCP client configuration

Register ChatBI in your client's MCP config pointing to the Python interpreter in the virtual environment.

{
  "mcpServers": {
    "chatbi": {
      "command": "/path/to/chatbi-mcp-server/.venv/bin/python",
      "args": ["/path/to/chatbi-mcp-server/src/pandas_mcp_server.py"]
    }
  }
}

ChatBI Examples

Client configuration

Claude Desktop config for ChatBI using the virtualenv Python interpreter.

{
  "mcpServers": {
    "chatbi": {
      "command": "/home/user/chatbi-mcp-server/.venv/bin/python",
      "args": ["/home/user/chatbi-mcp-server/src/pandas_mcp_server.py"]
    }
  }
}

Prompts to try

Example prompts for natural language data analysis on your Excel or CSV files.

- "Load sales_data.xlsx and show me total revenue by month for 2024."
- "Which product category had the highest average order value last quarter?"
- "Create a bar chart of monthly sales vs. target from the budget spreadsheet."
- "Find all rows in customer_data.csv where the churn risk score is above 0.8."
- "Summarize the key statistics (mean, median, std) for all numeric columns in report.xlsx."

Troubleshooting ChatBI

Server raises 'Python version not supported' or pandas import errors

Ensure your virtual environment was created with exactly Python 3.11 (uv venv .venv --python=3.11). Using Python 3.12+ or 3.10 may cause dependency conflicts.

LLM generates incorrect or empty code

Smaller models (below Qwen3-32B) frequently produce poor-quality data analysis code. Switch to GLM 4.5, Qwen-235B-A22B, or Kimi K2 for reliable results. Update the model name/endpoint in your .env file.

Server times out on large Excel files

Increase the LLM operation timeout in config.yaml. Large files take longer to process — also consider pre-filtering data to only the relevant sheets or columns before passing to the server.

Frequently Asked Questions about ChatBI

What is ChatBI?

ChatBI is a Model Context Protocol (MCP) server that 使用llm生成代码来对excel进行分析的mcp server It connects AI assistants to external tools and data sources through a standardized interface.

How do I install ChatBI?

Follow the installation instructions on the ChatBI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with ChatBI?

ChatBI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is ChatBI free to use?

Yes, ChatBI is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

ChatBI Alternatives — Similar Analytics Servers

Looking for alternatives to ChatBI? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.

OpenMetadata

★ 14.0k

OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.

Superset

★ 10.9k

An MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.

Horizon

★ 4.4k

📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达

MCP Server Chart

★ 4.1k

Enables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations

Muapi CLI

★ 997

Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.

Weather MCP Server

★ 907

Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien

Browse More Analytics MCP Servers

Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

AnalyticsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "chatbi": { "command": "npx", "args": ["-y", "chatbi"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use ChatBI?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides