Happy slice of mcp pizzaMCP.pizza

claude-code-mcp-enhanced

MCP.Pizza Chef: grahama1970

Assistants tend to lose their footing on long multi-step jobs. This hands the work to Claude Code running underneath, and splits a big request into smaller pieces that come back one at a time. The practical effect is that a job like refactoring across several files gets finished rather than abandoned halfway. It works in Claude Desktop, Cursor, and Windsurf, and installs through common package tools.

Unmaintained · No commits in 16 months.
Coding
Writing

Use This MCP server To

Break a big job into steps that finish Have changes made across several files Run a long task without babysitting it Retry a step that failed without starting over Hand off work that's too big for one go

README

🤖 Claude Code MCP Server

Want to get started quickly? Check out our QUICKSTART.md guide!

This project is a fork of steipete/claude-code-mcp with enhanced orchestration capabilities, reliability improvements, and additional documentation.

An enhanced Model Context Protocol (MCP) server that allows running Claude Code in one-shot mode with permissions bypassed automatically. This server includes advanced task orchestration capabilities, robust error handling, and a "boomerang pattern" for breaking complex tasks into manageable subtasks.

Did you notice that standard AI assistants sometimes struggle with complex, multi-step edits or operations? This server, with its powerful unified claude_code tool and enhanced reliability features, aims to make Claude a more direct and capable agent for your coding tasks.

Claude Code Example

🔍 Overview

This MCP server provides powerful tools that can be used by LLMs to interact with Claude Code. When integrated with Claude Desktop or other MCP clients, it allows LLMs to:

  • Run Claude Code with all permissions bypassed (using --dangerously-skip-permissions)
  • Execute Claude Code with any prompt without permission interruptions
  • Access file editing capabilities directly
  • Execute complex multi-step operations with robust error handling and retries
  • Orchestrate tasks through specialized agent roles using the boomerang pattern
  • Maintain reliable execution through heartbeat mechanisms to prevent timeouts

✨ Benefits

  • Enhanced Reliability: Robust error handling, automatic retries, graceful shutdown, and request tracking
  • Task Orchestration: Complex workflows can be broken down into specialized subtasks
  • Task Automation: Convert human-readable markdown task lists into executable MCP commands automatically
  • Performance Optimization: Improved execution with configuration caching and resource efficiency
  • Better Monitoring: Health check API, detailed error reporting, and comprehensive logging
  • Developer Experience: Hot reloading of configuration, flexible environment controls, and simplified API

Plus all the standard Claude Code benefits:

  • Claude/Windsurf often have trouble editing files. Claude Code is better and faster at it.
  • Multiple commands can be queued instead of direct execution. This saves context space so more important information is retained longer.
  • File ops, git, or other operations don't need costly models. Claude Code is cost-effective if you sign up for Anthropic Max.
  • Claude has wider system access, so when standard assistants are stuck, just ask them to "use claude code" to unblock progress.

📝 Prerequisites

  • Node.js v20 or later (Use fnm or nvm to install)
  • Claude CLI installed locally (run it and call /doctor) and -dangerously-skip-permissions accepted.

claude-code-mcp-enhanced FAQ

Can I use this for jobs too big for one request?
Yes — that is the point; it splits work into pieces and works through them.
Which apps does it work with?
It is documented for Claude Desktop, Cursor, and Windsurf.
Do I need an account or key?
No separate key for the server itself, but it runs Claude Code underneath, which needs its own access.
What happens if a step fails?
It handles errors and can retry a step rather than losing the whole run.
How hard is it to set up?
It installs through common package tools, so expect a technical first run.