Skip to main content
Glama
Claude Code MCP

Claude Code MCP

by jawkjiang

Claude Code MCP

An MCP (Model Context Protocol) server that wraps the Claude Code CLI, enabling other AI agents to interact with Claude Code programmatically.

npm version

Features

  • Session Management: Start, continue, and manage multiple conversation sessions

  • Streaming Output: Real-time output from Claude Code tasks

  • Interrupt Support: Stop running tasks at any time (like Ctrl+C)

  • Permission Delegation: When Claude Code needs permission, the outer agent can approve, deny, or redirect

  • Progress Monitoring: Check task progress and get partial outputs

Related MCP server: Claude Code Manager WAN

Installation

npm install -g @jawkjiang/claude-code-mcp

From source

git clone https://github.com/jawkjiang/claude-code-mcp.git
cd claude-code-mcp
npm install
npm run build

Prerequisites

Configuration

Add to your ~/.mcp.json:

{
  "mcpServers": {
    "claude-code": {
      "command": "npx",
      "args": ["@jawkjiang/claude-code-mcp"]
    }
  }
}

Using global install

{
  "mcpServers": {
    "claude-code": {
      "command": "claude-code-mcp"
    }
  }
}

Using local build

{
  "mcpServers": {
    "claude-code": {
      "command": "node",
      "args": ["/path/to/claude-code-mcp/dist/index.js"]
    }
  }
}

Available Tools

Tool

Description

chat

Start a new conversation or continue an existing session

respond

Respond to permission requests: approve, deny, or redirect with new instructions

interrupt

Stop a running task (like Ctrl+C)

get_output

Get current output/progress from a session

list_sessions

List all active sessions

close_session

Close and cleanup a session

get_version

Get Claude Code CLI version

Usage Examples

Basic Chat

{
  "tool": "chat",
  "params": {
    "message": "Create a hello world Python script",
    "workingDirectory": "/path/to/project"
  }
}

Permission Handling

When Claude Code needs permission, you'll receive:

{
  "status": "awaiting_permission",
  "sessionId": "abc-123",
  "pendingPermission": {
    "tool": "Bash",
    "action": "rm -rf /tmp/test",
    "description": "Delete temporary directory"
  },
  "currentOutput": "I need to clean up the temp directory...",
  "message": "Use 'respond' tool to approve, deny, or redirect."
}

You can then respond with:

Approve:

{
  "tool": "respond",
  "params": {
    "sessionId": "abc-123",
    "action": "approve"
  }
}

Deny:

{
  "tool": "respond",
  "params": {
    "sessionId": "abc-123",
    "action": "deny"
  }
}

Redirect (provide alternative instructions):

{
  "tool": "respond",
  "params": {
    "sessionId": "abc-123",
    "action": "redirect",
    "message": "Don't delete the directory. Instead, just remove the .tmp files inside it."
  }
}

Interrupt a Task

{
  "tool": "interrupt",
  "params": {
    "sessionId": "abc-123"
  }
}

Architecture

Outer Agent                    claude-code-mcp                Claude Code CLI
    │                              │                              │
    │── chat(message) ────────────>│                              │
    │                              │──── spawn process ──────────>│
    │                              │                              │
    │<── awaiting_permission ─────│<── permission request ───────│
    │                              │                              │
    │── respond(action) ──────────>│                              │
    │   - approve                  │──── send response ──────────>│
    │   - deny                     │                              │
    │   - redirect(new_message)    │                              │
    │                              │                              │
    │<── completed ───────────────│<── task complete ────────────│

Permission Checkpoint Philosophy

Permission requests are not just approve/deny gates - they are audit and steering points where the outer agent can:

  1. Review what Claude Code is doing

  2. Approve and let it continue

  3. Deny and stop the current operation

  4. Redirect with new instructions ("No, do this instead...")

This gives the outer agent the same level of control a human would have when using Claude Code interactively.

License

MIT

Author

Created with Claude Code

Available Tools

7 tools
chatA

Start a new conversation with Claude Code or continue an existing session. Returns sessionId for future interactions. If permission is required, status will be "awaiting_permission" - use "respond" to approve/deny/redirect.

Inputs: message (required), model, sessionId, workingDirectory.

close_sessionB

Close and cleanup a session, freeing resources.

Inputs: sessionId (required).

get_outputA

Get the current output buffer from a running or completed session. Useful for checking progress.

Inputs: sessionId.

get_versionA

Get the installed Claude Code CLI version.

Inputs: no named parameters.

interruptA

Interrupt/stop the currently running Claude Code task. Like pressing Ctrl+C.

Inputs: sessionId.

list_sessionsA

List all active sessions and their status.

Inputs: no named parameters.

respondA

Respond to a permission request or send new instructions to Claude Code. Actions:

  • "approve": Allow the pending operation

  • "approve_all": Allow this and similar future operations

  • "deny": Reject the pending operation

  • "redirect": Stop current operation and provide new instructions instead

Inputs: action (required), message, sessionId.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation3/5

    chat and respond have overlapping capabilities: both can send messages to an existing session, though respond is primarily for permission handling. Other tools are clearly distinct, but the boundary between chat and respond may cause misselection.

    Naming Consistency4/5

    Most tools follow a verb or verb_noun pattern (chat, interrupt, get_output, list_sessions), but the mix of single verbs and prefixed verbs (get_, list_, close_) is a minor inconsistency.

    Tool Count5/5

    Seven tools is an appropriate scope for managing Claude Code sessions, covering all necessary operations without bloat or deficiency.

    Completeness5/5

    The set covers the full session lifecycle: create/resume (chat), interact (respond), monitor (get_output, list_sessions), interrupt, and close (close_session), plus version check. No obvious gaps.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables MCP clients to spawn and control Codex CLI and Claude Code sessions on the host machine, with session management and filesystem access.
      4
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables ISLI agents and MCP clients to dispatch natural-language coding and terminal tasks to a locally-installed Claude Code CLI, supporting both one-shot execution and persistent sessions with workspace and security controls.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables voice assistants to start, monitor, message, and approve local Claude Code sessions on your computer, including sessions already open in a terminal. It exposes session management, recaps, approvals, and history search as MCP tools.
      8
      GPL 3.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables a Claude Desktop or Claude Code session to start, drive, and supervise interactive Claude Code CLI worker runs, including sending prompts, reading terminal output, waiting for completion, stopping runs, and managing settings and permissions.
      MIT