code

Code-MCP bridges Claude AI to your development workflow, enabling terminal commands and file operations directly from the AI interface. It provides terminal access to run shell commands in your project directory, sophisticated file operations (read, edit, create, delete files and directories), and specialized handling for git commands to add safety confirmations. Beyond basic editing, Code-MCP offers smart editing and code analysis features that assist with function-level edits, pattern matching, and batch operations across multiple files. For teams or remote work, it also supports remote connectivity so Claude can interact with code repositories and environments located on remote servers via SSH.

Prerequisites:

• Python 3.10+ (or uv for Python environments)
• Access to pip or uv-pip for installing Python packages
• Git installed if you plan to install from GitHub

1. Quick install (base version) macOS / Linux:

# Install with a single command (includes uv installation if needed)
curl -LsSf https://raw.githubusercontent.com/54yyyu/code-mcp/main/install.sh | sh

Windows:

# Download and run the installer
powershell -c "Invoke-WebRequest -Uri https://raw.githubusercontent.com/54yyyu/code-mcp/main/install.ps1 -OutFile install.ps1; .\install.ps1"

2. Manual installation

# Install with pip
pip install git+https://github.com/54yyyu/code-mcp.git

# Or better, install with uv
uv pip install git+https://github.com/54yyyu/code-mcp.git

3. Optional Features (choose as needed) Remote Connectivity Support

# Install with remote connectivity support
pip install git+https://github.com/54yyyu/code-mcp.git@remote-edit

# Or with uv
uv pip install git+https://github.com/54yyyu/code-mcp.git@remote-edit

# One-line installer
curl -LsSf https://raw.githubusercontent.com/54yyyu/code-mcp/remote-edit/install.sh | sh

Jupyter Notebook Support

# Install with Jupyter notebook support
pip install git+https://github.com/54yyyu/code-mcp.git@jupyter

# Or with uv
uv pip install git+https://github.com/54yyyu/code-mcp.git@jupyter

# One-line installer
curl -LsSf https://raw.githubusercontent.com/54yyyu/code-mcp/jupyter/install.sh | sh

Combining Features (example)

# Clone the repository
git clone https://github.com/54yyyu/code-mcp.git
cd code-mcp

# Create a custom branch with both features
git checkout main
git merge remote-edit --no-commit
git merge jupyter --no-commit
git commit -m "Custom installation with both remote and jupyter features"

# Install from your custom branch
pip install -e .

For Developers

# Clone the repository
git clone https://github.com/54yyyu/code-mcp.git
cd code-mcp

# Install in development mode with pip
pip install -e .

# Or with uv (recommended)
uv pip install -e .

Tips and common issues:

• The mcpServers entry uses a simple command/argument setup. In most local setups, a server named 'code' with command 'code-mcp' and an argument path to your project is sufficient.
• If Claude Desktop requires absolute paths in the config, use the code-mcp-setup --fix-path helper to update to PATH-based usage. New installations default to PATH-based invocation.
• Remote Connectivity requires SSH access and Python 3.10+ on both sides. The remote installer handles installation, bridge script upload, and SSH tunneling automatically.
• Cloud/remote usage enables working with codebases on remote servers, VMs, or containers as if they were local. Terminate the SSH tunnel with Ctrl+C when done to clean up.
• Safety features include confirmation prompts for destructive operations (delete/overwrite) and path safety checks to keep operations within the project directory.
• Claude Desktop integration steps are documented in the README, including editing claude_desktop_config.json or using the code-mcp-setup helper.