MCP Claude Code
An implementation of Claude Code capabilities using the Model Context Protocol (MCP).
Overview
This project provides an MCP server that implements Claude Code-like functionality, allowing Claude to directly execute instructions for modifying and improving project files. By leveraging the Model Context Protocol, this implementation enables seamless integration with various MCP clients including Claude Desktop.
Features
- Code Understanding: Analyze and understand codebases through file access and pattern searching
- Code Modification: Make targeted edits to files with proper permission handling
- Enhanced Command Execution: Run commands and scripts in various languages with improved error handling and shell support
- File Operations: Manage files with proper security controls through shell commands
- Code Discovery: Find relevant files and code patterns across your project
- Agent Delegation: Delegate complex tasks to specialized sub-agents that can work concurrently
- Multiple LLM Provider Support: Configure any LiteLLM-compatible model for agent operations
- Jupyter Notebook Support: Read and edit Jupyter notebooks with full cell and output handling
Tools Implemented
Tool | Description |
---|---|
read_files | Read one or multiple files with encoding detection |
write_file | Create or overwrite files |
edit_file | Make line-based edits to text files |
directory_tree | Get a recursive tree view of directories |
get_file_info | Get metadata about a file or directory |
search_content | Search for patterns in file contents |
content_replace | Replace patterns in file contents |
grep_ast | Search code with AST context showing matches within functions, classes, and other structures |
run_command | Execute shell commands (also used for directory creation, file moving, and directory listing) |
run_script | Execute scripts with specified interpreters |
script_tool | Execute scripts in specific programming languages |
read_notebook | Extract and read source code from all cells in a Jupyter notebook with outputs |
edit_notebook | Edit, insert, or delete cells in a Jupyter notebook |
think | Structured space for complex reasoning and analysis without making changes |
dispatch_agent | Launch one or more agents that can perform tasks using read-only tools concurrently |
Getting Started
For detailed installation and configuration instructions, please refer to INSTALL.md.
Of course, you can also read USEFUL_PROMPTS for some inspiration on how to use mcp-claude-code.
Security
This implementation follows best practices for securing access to your filesystem:
- Permission prompts for file modifications and command execution
- Restricted access to specified directories only
- Input validation and sanitization
- Proper error handling and reporting
Development
To contribute to this project:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add some amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
An MCP server that implements Claude Code-like functionality, allowing the AI to analyze codebases, modify files, execute commands, and manage projects through direct file system interactions.
Related MCP Servers
- -securityFlicense-qualityAn MCP server that allows Claude AI to perform filesystem operations including reading, writing, listing, moving files, and searching directories within specified allowed paths.Last updated -51JavaScript
- -securityAlicense-qualityA local MCP server that enables AI applications like Claude Desktop to securely access and work with Obsidian vaults, providing capabilities for reading notes, executing templates, and performing semantic searches.Last updated -60TypeScriptMIT License
- -securityFlicense-qualityAn MCP server that allows AI assistants like Claude to execute terminal commands on the user's computer and return the output, functioning like a terminal through AI.Last updated -7Python
- -securityAlicense-qualityAn MCP server that analyzes codebases and generates contextual prompts, making it easier for AI assistants to understand and work with code repositories.Last updated -2PythonMIT License