About repo-to-txt-mcp
repo-to-txt-mcp analyzes Git repositories or local folders and converts them into structured text for LLM context. It is intended for developers using repository context in applications such as Cursor, with file filtering and output-size limits.
Key features
- 01Analyze local and remote repositories
- 02Generate structured text with file contents
- 03Filter files by extension
- 04Limit output by token count
- 05Integrate with Cursor's MCP system
Use cases
- 01Preparing repository context for an LLM
- 02Selecting source files for analysis
- 03Capping repository text output
MCP support
It exposes repository analysis and text-conversion functionality as an MCP server, designed to provide repository context to MCP clients such as Cursor.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMErepo-to-txt-mcp
An MCP server for analyzing and converting Git repositories to text files for LLM context.
Overview
repo-to-txt-mcp is a Machine Code Protocol (MCP) server that allows you to analyze GitHub repositories or local folders and convert them into structured text files. This is particularly useful for providing context about repositories to large language models (LLMs) like GPT-4.
This project extends the functionality of the repo-to-txt CLI tool to provide a web API that can be integrated into other applications, particularly Cursor's MCP system.
Features
- Repository Analysis: Analyze both local and remote Git repositories
- Structured Output: Generate formatted text with folder structure and concatenated file contents
- File Filtering: Include or exclude files based on extensions
- Token Management: Limit output size by token count
- Easy Integration: Designed to work seamlessly with Cursor's MCP system
- Cross-Platform: Works on Windows, macOS, and Linux
Installation
Prerequisites
- Python 3.8+
- Node.js 14+
- Git
Installation Options
See the Installation Guide for detailed instructions on:
- Direct installation
- Docker installation
- GitHub Container Registry usage
Quick Start
-
Install the required packages:
pip install -r requirements.txt npm install -
Start the server:
node smithery-wrapper.js -
The server will be available at
http://localhost:8000
API Usage
Convert a GitHub Repository
curl -X POST http://localhost:8000/analyze \
-H "Content-Type: application/json" \
-d '{
"source": "https://github.com/username/repository",
"return_file": true
}'
Filter by File Extensions
curl -X POST http://localhost:8000/analyze \
-H "Content-Type: application/json" \
-d '{
"source": "https://github.com/username/repository",
"include_only": [".py", ".js", ".md"],
"exclude": [".pyc", ".git"]
}'
See the API Documentation for complete details.
Cursor Integration
This server is designed to integrate with Cursor to provide repository context to language models during conversations.
See the Cursor Integration Guide for instructions on how to set up and use this feature.
Docker Support
A Dockerfile is included to facilitate containerized deployment:
docker build -t repo-to-txt-mcp .
docker run -p 8000:8000 repo-to-txt-mcp
Smithery Integration
This project includes configuration for Smithery, a tool for managing MCPs:
smithery install chromewillow/repo-to-txt-mcp
Contributing
Contributions are welcome! Please see CONTRIBUTING.md for guidelines.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- This project builds on the functionality of the repo-to-txt CLI tool
- Thanks to the FastMCP library for simplifying the creation of MCP servers
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.