RepoMix MCP server for AI agents

Repomix is a tool that packages your codebase into AI-friendly formats, making it easier to analyze your code with AI assistants like ChatGPT, Claude, or Gemini. It generates a single file containing your entire repository in a structured format that AI models can understand and process effectively.

Installation

You can use Repomix without installing it:

npx repomix@latest

Or install it globally for repeated use:

# Install using npm
npm install -g repomix

# Alternatively using yarn
yarn global add repomix

# Alternatively using bun
bun add -g repomix

# Alternatively using Homebrew (macOS/Linux)
brew install repomix

Basic Usage

To pack your entire repository:

repomix

This generates a repomix-output.xml file in your current directory that you can send to an AI assistant.

To pack a specific directory:

repomix path/to/directory

To include or exclude specific files:

# Include specific files or patterns
repomix --include "src/**/*.ts,**/*.md"

# Exclude specific files or patterns
repomix --ignore "**/*.log,tmp/"

Remote Repository Processing

You can pack a remote GitHub repository:

# Full URL
repomix --remote https://github.com/yamadashy/repomix

# GitHub shorthand
repomix --remote yamadashy/repomix

# Specify branch or commit
repomix --remote yamadashy/repomix --remote-branch main

Advanced Features

Code Compression

Reduce token count while preserving code structure:

repomix --compress

File Selection via stdin

Process files from a list (pipe via stdin):

# Using find command
find src -name "*.ts" -type f | repomix --stdin

# Using git to get tracked files
git ls-files "*.ts" | repomix --stdin

Include Git Information

# Include git logs with default count (50 commits)
repomix --include-logs

# Include git diffs for changes
repomix --include-diffs

Token Count Analysis

View token distribution across your codebase:

repomix --token-count-tree

Output Formats

Choose from multiple output formats:

# XML format (default)
repomix --style xml

# Markdown format
repomix --style markdown

# JSON format
repomix --style json

# Plain text format
repomix --style plain

Docker Usage

Run Repomix in an isolated Docker container:

# Current directory
docker run -v .:/app -it --rm ghcr.io/yamadashy/repomix

# Remote repository
docker run -v ./output:/app -it --rm ghcr.io/yamadashy/repomix --remote yamadashy/repomix

MCP Server Integration

Run Repomix as a Model Context Protocol server for AI tool integration:

repomix --mcp

You can install the Repomix MCP server in VS Code with this command:

code --add-mcp '{"name":"repomix","command":"npx","args":["-y","repomix","--mcp"]}'

Configuration

You can create a configuration file:

# Initialize config file in current directory
repomix --init

# Create global config
repomix --init --global

This creates a repomix.config.json file with customizable options, including:

Output file path and format
Included/excluded file patterns
Token counting options
Git integration settings
Security checks
And many more options

Prompt Examples

After generating your packed file, use these sample prompts with AI tools:

This file contains my entire codebase. Please review the overall structure and suggest any improvements or refactoring opportunities, focusing on maintainability and scalability.

Or:

Review the codebase for adherence to coding best practices and industry standards. Identify areas where the code could be improved in terms of readability, maintainability, and efficiency.

Security Features

Repomix includes security scanning to prevent sensitive information exposure:

# Disable security check (use with caution)
repomix --no-security-check

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "repomix" '{"command":"npx","args":["-y","repomix","--mcp"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect