Happy slice of mcp pizzaMCP.pizza

mcp-claude-code

MCP.Pizza Chef: SDGLBL

Give your assistant access to a folder and it can read files, make precise edits, create new ones, search quickly for patterns, run commands in a terminal, and open or change Jupyter notebooks — much of what a coding helper in a terminal does, but from inside Claude Desktop. It asks before changing anything and stays within the folders you allow. The last change to the project landed in August 2025, and no successor is named.

Unmaintained · nothing changed since August 2025, no successor named
Coding

Use This MCP server To

Ask for a bug fix and have the file actually changed Search my project for every place a setting is used Run my tests and get an explanation of what failed Walk through a Jupyter notebook and clean up its cells Rename one thing consistently across many files Get a tour of a project I have never opened before

README

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.

example

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 with high-performance searching
  • 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 Read file contents with line numbers, offset, and limit capabilities
write Create or overwrite files
edit Make line-based edits to text files
multi_edit Make multiple precise text replacements in a single file operation with atomic transactions
directory_tree Get a recursive tree view of directories
grep Fast pattern search in files with ripgrep integration for best performance (docs)
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)
notebook_read Extract and read source code from all cells in a Jupyter notebook with outputs
notebook_edit 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
batch Execute multiple tool invocations in parallel or serially in a single request
todo_write Create and manage a structured task list
todo_read Read a structured task list

mcp-claude-code FAQ

Is this still maintained?
It looks dormant. The repository is not archived, but nothing has changed since August 2025 and the author names no replacement.
Which apps does it work in?
Claude Desktop is the documented target, and other apps that speak the same protocol can connect as well.
Will it edit my files without asking?
No. It prompts before changing files or running commands, and it is limited to the folders you specifically allow.
Do I need a paid key?
Not for the everyday tools, which run locally. Handing work to its background helpers uses an outside model provider, which does need an account.
Can I use this to fix a bug in my project?
Yes. Point it at the folder, let it search for the cause, and it can make the edit for you once you approve.
How hard is the setup?
This is a developer install: you set the package up yourself and hand-edit a settings file listing the folders it may touch.
Does it run commands on my computer?
Yes, it can run terminal commands, which is powerful enough that you should limit it to a project folder you trust it with.