What is Claude Code MCP — Run Claude as Agent-in-Agent?

MCP server that runs Claude Code CLI in one-shot mode inside other AI tools. Enables Cursor, Windsurf, and Claude Desktop to delegate complex tasks to Claude Code. 1.2K+ stars, MIT.

Is Claude Code MCP — Run Claude as Agent-in-Agent free to use?

Yes. Claude Code MCP — Run Claude as Agent-in-Agent is freely available on TokRepo. Check the Source & Thanks section on the asset page for the specific open-source license.

How do I install Claude Code MCP — Run Claude as Agent-in-Agent?

Visit the asset page on TokRepo and click "Copy for agent" to get the installation instructions. Most assets can be installed with a single command.

Claude Code MCP — Run Claude as Agent-in-Agent

Introduction

Claude Code MCP is an MCP server that runs the Claude Code CLI in single-execution mode from inside Cursor, Windsurf, Claude Desktop, and other tools. 1,200+ GitHub stars, MIT open source. It turns Claude Code into an "agent inside an agent" — your primary AI tool can delegate complex file edits, Git operations, and terminal commands to Claude Code, without interactive permission prompts.

Why Use Claude Code MCP?

Complex file editing — Claude Code outperforms most editors on multi-file refactors
Git operations — stage, commit, push without switching tools
Terminal execution — run build, test, and deploy commands
Context offload — delegate tasks to Claude Code to conserve your primary tool's context window

How It Works

The primary AI tool encounters a complex task
It calls the claude_code MCP tool with a prompt
Claude Code CLI executes the task with full filesystem permissions
Results are returned to the primary AI tool

Claude Code MCP — Run Claude as Agent-in-Agent

Introduction

Why Use Claude Code MCP?

How It Works

来源与感谢

讨论