mcpField
C
Claude Orchestration MCP Server

Claude Orchestration MCP Server

Local
github.com/claude-did-thisAI & Agents8Updated 73w ago
Repository

About Claude Orchestration MCP Server

A server for coordinating multiple Claude Code sessions on complex projects, intended for parallel work. It manages session dependencies and progress, retrieves outputs, and includes a Gradio web interface.

Key features

  1. 01Create and manage sessions
  2. 02Set session dependencies
  3. 03Track status and progress
  4. 04Retrieve session outputs
  5. 05Gradio web interface

Use cases

  1. 01Run project tasks across parallel sessions
  2. 02Coordinate sessions with dependencies
  3. 03Check progress and collect completed outputs

MCP support

The server exposes tools to create, start, list, monitor, wait for, and retrieve output from Claude Code sessions for MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Claude Orchestration MCP Server

An MCP (Model Context Protocol) server for orchestrating multiple Claude Code sessions to work on complex projects in parallel.

Features

  • Create and manage multiple Claude Code sessions
  • Define dependencies between sessions
  • Monitor session progress and status
  • Retrieve session outputs
  • Web-based interface using Gradio

Setup

  1. Install dependencies:
pip install gradio httpx python-dotenv

  1. Configure environment variables:

    • Copy .env.example to .env
    • Update CLAUDE_WEBHOOK_SECRET with your actual webhook secret

  2. Run the server:

./run_server.sh
# or
python mcp_server.py

The server will start at http://localhost:7860

API Endpoints

The server exposes the following tools:

  • create_session: Create a new Claude Code session
  • start_session: Start a previously created session
  • get_session_status: Check the status of a session
  • get_session_output: Retrieve output from a completed session
  • list_sessions: List all sessions with optional filtering
  • wait_for_session: Wait for a session to complete

Testing

Run the test script to verify your configuration:

python test_mcp_server.py

Authentication

The server uses Bearer token authentication. Set your webhook secret in the .env file:

CLAUDE_WEBHOOK_SECRET=your-secret-here

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.