CSV Editor
Stateful CSV editing MCP server for AI assistants — sessions, undo/redo, auto-save, and 39 pandas-powered tools. Works with Claude, ChatGPT, Cursor, Windsurf, Claude Code, and any MCP-compatible client. Built on FastMCP 3
What is CSV Editor?
CSV Editor is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to stateful csv editing mcp server for ai assistants — sessions, undo/redo, auto-save, and 39 pandas-powered tools. works with claude, chatgpt, cursor, windsurf, claude code, and any mcp-compatible clien...
Stateful CSV editing MCP server for AI assistants — sessions, undo/redo, auto-save, and 39 pandas-powered tools. Works with Claude, ChatGPT, Cursor, Windsurf, Claude Code, and any MCP-compatible client. Built on FastMCP 3
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Stateful CSV editing MCP server for AI assistants — sessions
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx csv-editorConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use CSV Editor
The CSV Editor MCP server provides AI assistants with a stateful, session-based environment for reading, transforming, analyzing, and exporting CSV files using 39 pandas-powered tools. It supports undo/redo with snapshots, configurable auto-save, multi-session management, and data I/O in CSV, JSON, Excel, Parquet, HTML, and Markdown formats. Built on FastMCP 3, it works with Claude, ChatGPT, Cursor, Windsurf, Claude Code, and any other MCP-compatible client, making it the go-to tool for natural-language data wrangling without writing pandas code manually.
Prerequisites
- Python 3.9 or later
- uv package manager (recommended) or pip
- Git (for cloning the repository installation method)
- An MCP-compatible client such as Claude Desktop, Claude Code, Cursor, or Windsurf
Install via Smithery (quickest method)
Use the Smithery CLI to install and configure the CSV Editor for Claude in one command.
npx -y @smithery/cli install @santoshray02/csv-editor --client claudeInstall manually using uv
Clone the repo and sync dependencies with uv for a self-contained installation.
git clone https://github.com/santoshray02/csv-editor.git
cd csv-editor
uv sync
uv run csv-editorConfigure Claude Desktop manually
Add the CSV Editor to your Claude Desktop configuration file. On macOS this is at ~/Library/Application Support/Claude/claude_desktop_config.json.
{
"mcpServers": {
"csv-editor": {
"command": "uv",
"args": ["tool", "run", "csv-editor"],
"env": {
"CSV_MAX_FILE_SIZE": "1073741824"
}
}
}
}Set environment variables for your use case
Configure optional environment variables to tune file size limits, session timeout, and history storage.
# In your shell or MCP server env block:
CSV_MAX_FILE_SIZE=1073741824 # 1 GB max file size (default: 1024 MB)
CSV_SESSION_TIMEOUT=120 # session timeout in minutes (default: 60)
CSV_EDITOR_CSV_HISTORY_DIR=.csv_history # undo/redo snapshot directoryLoad a CSV file and start working
Once the server is running and connected to your client, load a CSV file to begin a session. You can then issue natural language commands to transform it.
CSV Editor Examples
Client configuration
Claude Desktop configuration to run the CSV Editor using uv with a 1 GB file size limit.
{
"mcpServers": {
"csv-editor": {
"command": "uv",
"args": ["tool", "run", "csv-editor"],
"env": {
"CSV_MAX_FILE_SIZE": "1073741824",
"CSV_SESSION_TIMEOUT": "60"
}
}
}
}Prompts to try
Natural language commands that map to the server's 39 pandas-powered tools.
- "Load /data/sales_2024.csv and show me a summary of all columns"
- "Remove duplicate rows and fill missing values in the revenue column with the median"
- "Filter for Q4 2024 transactions where amount is greater than 10000"
- "Calculate the correlation matrix between price, quantity, and discount"
- "Detect outliers in the response_time column using IQR and show me their row indices"
- "Export the cleaned data to Parquet format"
- "Undo the last three changes"Troubleshooting CSV Editor
uv tool run csv-editor fails with package not found
The PyPI package may not be published yet. Install from source instead: clone the repo, run `uv sync`, then run `uv run csv-editor` from inside the cloned directory, updating the args in your MCP config accordingly.
Session expires in the middle of a long data cleaning workflow
Increase the CSV_SESSION_TIMEOUT environment variable in your MCP config. Set it to a higher value in minutes, e.g. 240 for a 4-hour session.
Large CSV files cause slow responses or timeouts
Increase CSV_MAX_FILE_SIZE if files are being rejected, and consider splitting very large files (>500 MB) into chunks before loading. Ensure your machine has enough RAM — pandas loads the full file into memory.
Frequently Asked Questions about CSV Editor
What is CSV Editor?
CSV Editor is a Model Context Protocol (MCP) server that stateful csv editing mcp server for ai assistants — sessions, undo/redo, auto-save, and 39 pandas-powered tools. works with claude, chatgpt, cursor, windsurf, claude code, and any mcp-compatible client. built on fastmcp 3 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install CSV Editor?
Follow the installation instructions on the CSV Editor GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with CSV Editor?
CSV Editor works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is CSV Editor free to use?
Yes, CSV Editor is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
CSV Editor Alternatives — Similar Data Science & ML Servers
Looking for alternatives to CSV Editor? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA 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
★ 2.1kAix-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
★ 1.7kOpen 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
★ 1.5kBridges 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.
Set Up CSV Editor in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use CSV Editor?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.