
Claude Code
The Claude Code MCP server provides a unified `claude_code` tool that allows LLMs to execute Claude Code in one-shot mode with permissions automatically bypassed, enabling direct file editing and multi-step operations without interruption. It solves problems where Claude Desktop or Cursor struggle with complex edits by offloading tasks to Claude Code, which can queue multiple commands efficiently while reducing context overhead. The server requires Node.js v20+ and a local Claude CLI installation, and supports configuration through environment variables to customize the CLI binary used.
- GitHub stars
- 1.3K
- tool
- 1
- last updated
- Mar 6, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
claude_codeExecutes a prompt directly using the Claude Code CLI. Defaults to bypassed permissions for backwards compatibility; pass `permissionMode` to use Claude Code's native permission modes.
Executes a prompt directly using the Claude Code CLI. Defaults to bypassed permissions for backwards compatibility; pass `permissionMode` to use Claude Code's native permission modes.
No parameter schema in public metadata yet.
Sponsors
Readme
Claude Code MCP Server
Claude Code MCP LogoAn MCP (Model Context Protocol) server that allows running Claude Code in one-shot mode, with bypassed permissions by default and optional native Claude Code permission modes.
Did you notice that Cursor sometimes struggles with complex, multi-step edits or operations? This server, with its powerful unified claude_code tool, aims to make Claude a more direct and capable agent for your coding tasks.
Overview
This MCP server provides one tool that can be used by LLMs to interact with Claude Code. When integrated with Claude Desktop or other MCP clients, it allows LLMs to:
Details
- Repository
- github.com/steipete/claude-code-mcp
- Category
- AI & LLM Tools