Search

More Filters

Show More
Add Listing
Go Back

claude code mcp

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

This repository provides a small MCP (Model Context Protocol) server that exposes a single unified tool allowing LLM-based clients to run the Claude Code CLI in one-shot mode with permissions bypassed. It is intended to be integrated with MCP-aware clients such as Cursor or Windsurf so an LLM agent can execute concrete coding and system tasks through the claude_code tool. The server forwards prompts to the local Claude Code binary using the --dangerously-skip-permissions mode after an initial manual acceptance step. It supports configuration via environment variables, client mcp.json configuration, and examples for file editing, git operations, terminal commands and multi-step workflows. The README documents prerequisites, installation via npx, first-time setup requirements, and recommended MCP configuration paths for common clients.

Links

Stars
724
App URL
https://github.com/steipete/claude-code-mcp
Github Repository
https://github.com/steipete/claude-code-mcp/blob/main/README.md

Categorization

App Details

Features
The project exposes a primary tool named claude_code that accepts a prompt and optional options including which Claude tools to enable. It runs the local Claude Code CLI with --dangerously-skip-permissions to avoid interactive permission prompts. Supported capabilities documented include file system operations (create, read, edit, move, delete), git workflows (stage, commit, push, tag), running terminal commands, web search and summarization, and complex multi-step automation such as preparing releases and fixing CI workflows. Configuration options include environment variables to override the Claude binary name or path and a debug flag for verbose logging. The package includes npx installation guidance, MCP client configuration examples, visual examples, tests, and developer setup and testing scripts.
Use Cases
This server makes it straightforward for MCP clients and agents to delegate coding and repository tasks to Claude Code with fewer interruptions from permission checks, enabling faster file edits, refactors, and multi-step operations. It helps unstick other agents by providing a more capable code-oriented tool, reduces the need to use larger costly models for routine file and git operations, and centralizes access to file ops, git, and shell commands under a single tool. The documented examples show how to automate release workflows, fix lint and CI issues, create pull requests, and correct syntax errors, while environment variables and configurable CLI paths allow testing, customization, and local development. The README also explains first-time manual acceptance and troubleshooting steps to get the server working reliably.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*