MCPgee
MCPgee
MCPgeeMCPgee

Pandas

v1.0.0•Data Science & ML•stable

MCP server for pandas

pandasmcpai-integration
Share:
44
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Pandas?

Pandas is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for pandas

MCP server for pandas

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

Features

  • MCP server for pandas

Use Cases

Execute pandas dataframe operations through MCP.
marlonluo2018

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 16, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx pandas

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 Pandas

The Pandas MCP Server gives AI assistants direct access to pandas-powered data analysis workflows. It exposes four tools — metadata extraction, column interpretation, arbitrary pandas code execution, and Chart.js chart generation — so language models can read CSV, Excel, or JSON files, profile their structure, run custom data transformations, and produce interactive HTML charts. Data analysts and scientists use it to offload exploratory data analysis to an AI without copying data into the chat window.

Prerequisites

  • Python 3.9+ installed on your system
  • pip package manager and ability to install from a cloned repo
  • pandas, openpyxl, and other dependencies listed in requirements.txt
  • An MCP-compatible client such as Claude Desktop
  • Data files accessible on the local filesystem (CSV, Excel, JSON)
1

Clone the repository and install dependencies

Clone the pandas-mcp-server repository and install all Python dependencies from requirements.txt. A virtual environment is recommended to avoid conflicts.

git clone https://github.com/marlonluo2018/pandas-mcp-server.git
cd pandas-mcp-server
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
2

Configure the environment file

Copy .env.example to .env and adjust settings such as LOG_LEVEL, MAX_FILE_SIZE for upload limits, CHARTS_DIR for where generated HTML charts are saved, and feature flags to enable or disable chart generation and code execution.

cp .env.example .env
# Edit .env and set values such as:
# LOG_LEVEL=INFO
# MAX_FILE_SIZE=50MB
# CHARTS_DIR=./charts
3

Test the server locally using the CLI

Before connecting an MCP client, verify the server works with the built-in CLI. Run a metadata extraction on a sample file to confirm pandas can read it.

python cli.py metadata data.xlsx
4

Add the server to your MCP client configuration

Register the pandas MCP server in claude_desktop_config.json using the absolute path to your virtual environment's Python executable and the path to server.py.

{
  "mcpServers": {
    "pandas": {
      "command": "/absolute/path/to/pandas-mcp-server/.venv/bin/python",
      "args": ["/absolute/path/to/pandas-mcp-server/server.py"]
    }
  }
}
5

Restart Claude Desktop and run a data analysis

Restart Claude Desktop to load the new server. Provide a file path in your prompt and ask Claude to profile it using the read_metadata_tool. Generated charts are saved to the CHARTS_DIR and can be opened in a browser.

Pandas Examples

Client configuration

claude_desktop_config.json entry pointing to the cloned repository's Python environment and server entry point.

{
  "mcpServers": {
    "pandas": {
      "command": "/Users/yourname/pandas-mcp-server/.venv/bin/python",
      "args": ["/Users/yourname/pandas-mcp-server/server.py"]
    }
  }
}

Prompts to try

Example prompts using the four tools: read_metadata_tool, interpret_column_data, run_pandas_code_tool, and generate_chartjs_tool.

- "Extract the metadata and column statistics for /data/sales_2025.csv."
- "Interpret the 'Region' and 'Status' columns in /data/sales_2025.csv and show value frequencies."
- "Run pandas code to group /data/sales_2025.csv by Region and sum the Revenue column."
- "Generate a bar chart of monthly revenue from /data/sales_2025.csv with title 'Monthly Revenue 2025'."

Troubleshooting Pandas

ModuleNotFoundError for pandas or openpyxl when the server starts

Ensure you activated the virtual environment before installing requirements, and that the command in claude_desktop_config.json points to the venv Python executable, not the system Python.

File size exceeded or file not found errors when reading data files

Check the MAX_FILE_SIZE setting in your .env file and increase it if needed. Also verify that the file path provided in the prompt is an absolute path accessible to the server process.

Generated charts directory not found

Create the directory specified by CHARTS_DIR before running the server (e.g., mkdir -p ./charts). The server will write chart HTML files there; the directory must exist and be writable.

Frequently Asked Questions about Pandas

What is Pandas?

Pandas is a Model Context Protocol (MCP) server that mcp server for pandas It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Pandas?

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

Which AI clients work with Pandas?

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

Is Pandas free to use?

Yes, Pandas 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

Pandas Alternatives — Similar Data Science & ML Servers

Looking for alternatives to Pandas? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

Browse More Data Science & ML MCP Servers

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

Data Science & MLBrowse All Servers

Quick Config Preview

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

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

Read the full setup guide →

Ready to use Pandas?

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