claude-code MCP Server

Use This MCP server To

Hand a messy multi-file edit to a stronger coding helper Unstick my editor's assistant when it says it cannot do something Queue several file changes instead of approving each one by hand Send routine file and version-control chores to a cheaper helper Ask one assistant to call another for the heavy lifting

README

Claude Code MCP Server

Claude Code MCP Logo

View changelog

An 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.

Screenshot

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:

Run Claude Code with all permissions bypassed by default (using --dangerously-skip-permissions)
Execute Claude Code with a native permission mode when requested
Access file editing capabilities directly
Enable specific tools by default

Permissions and Alternatives

This server is a thin MCP wrapper around the local Claude Code CLI. By default it preserves the historic behavior and starts Claude Code with --dangerously-skip-permissions. Set the tool's permissionMode argument to default, acceptEdits, auto, dontAsk, or plan when you want Claude Code's native permission checks instead. This wrapper is not an OS-level sandbox; for a hard file-system boundary, run the MCP server or Claude CLI inside your own container, VM, or platform sandbox.

The wrapper cannot approve prompts that belong to a parent MCP client, bypass macOS privacy prompts, or make another Claude Code session inherit its settings. If the calling client stalls while waiting for permission checks, fix the caller's MCP permissions or run Claude Code directly instead.

Current alternatives:

Use Claude Code directly for work that needs its native permission UI: claude, claude -p, or claude --permission-mode default.
Use Claude Code's native MCP server when another MCP client should access Claude Code tools: claude mcp serve.
For Claude Code as the caller, configure tool permissions with --allowedTools, --disallowedTools, project/user settings, or --permission-prompt-tool.

Use this package when you specifically want one MCP tool that delegates a prompt to a separate Claude Code process. Prefer native Claude Code MCP/permission configuration when permission ownership needs to stay with the active Claude Code session.

Benefits

claude-code-mcp FAQ

Which apps does this work in?

Claude Desktop, Cursor, and Windsurf, by pasting a short block into each app's settings file.

Do I need to buy a key?

No separate key, but you do need the Claude Code command-line app installed and signed in on the same computer.

Can I use this to fix a file my editor keeps mangling?

Yes — tell your assistant to use Claude Code and it passes the edit along to a tool that handles files better.

How hard is setup?

Roughly ten minutes: install Node 20 or newer, run the Claude command once to accept its terms, then paste a few lines of settings.

Is it safe to let it change my files?

It skips permission prompts by default, so use it on work you can undo, or switch it to a mode that asks before each step.

Does it replace Claude Code itself?

No. It is a thin wrapper, and the authors suggest using Claude Code directly when you want its own permission prompts.