Seatunnel

🚀 SeaTunnel MCP Server

A Model Context Protocol (MCP) server for interacting with SeaTunnel via Large Language Model (LLM) interfaces.

🚀 Quick Start

To better understand the features and usage of Seatunnel MCP, we provide a demonstration video. Please refer to the following link or directly view the video file in the project documentation directory.

https://www.youtube.com/watch?v=JaLA8EkZD7Q

⚠️ Important Note

If the video cannot be played directly, please ensure that your device supports the MP4 format and try opening it with a modern browser or video player.

✨ Features

• Job management (submit, stop, monitor)
• System information query and retrieval
• Interaction with the REST API of SeaTunnel services
• Built-in logging and monitoring tools
• Dynamic connection configuration
• Comprehensive job information and statistics

📦 Installation

# Clone the repository
git clone <repository_url>
cd seatunnel-mcp

# Create a virtual environment and install
python -m venv .venv
source .venv/bin/activate  # For Windows: .venv\Scripts\activate
pip install -e .

📚 Documentation

Configuration Requirements

• Python ≥ 3.12
• A running SeaTunnel instance
• Node.js (for testing with MCP Inspector)

Usage

Environment Variables

SEATUNNEL_API_URL=http://localhost:8090  # Default SeaTunnel REST API URL
SEATUNNEL_API_KEY=your_api_key           # Optional: Default SeaTunnel API key

Dynamic Connection Configuration

The server provides tools to view and update connection settings:

• get-connection-settings: View the current connection URL and API key status
• update-connection-settings: Update the URL and/or API key to connect to a different SeaTunnel instance

Usage through MCP examples:

// Get current settings
{
  "name": "get-connection-settings"
}

// Update connection settings
{
  "name": "update-connection-settings",
  "arguments": {
    "url": "http://new-host:8090",
    "api_key": "new-api-key"
  }
}

Job Management

The server provides tools to submit and manage SeaTunnel jobs:

• submit-job: Submit a new job with job configuration
• submit-jobs: Submit multiple jobs at once
• stop-job: Stop a specified job
• monitor-jobs: Monitor job status

Run the Server

# Run the following command in the terminal to start the server:
python -m seatunnel_mcp_server

Integration with Claude Desktop

To use the Seatunnel MCP Server in Claude Desktop, follow these steps to configure:

1. Open the settings in Claude Desktop.
2. Add a new API endpoint with the URL http://localhost:8090.
3. Select this endpoint in the project for interaction.

Testing

Run the following command to test the connection to the MCP server:

curl http://localhost:8090/health

Changelog

v1.1.0 (Latest Version)

• Fixed a bug in the dynamic connection configuration tool that prevented the API key from being updated correctly.
• Improved the job monitoring function, now supporting real-time status updates.

v1.0.1

• Added support for JSON format job configuration.
• Optimized the integration experience with Claude Desktop.

v1.0.0 (Initial Version)

• First release with basic SeaTunnel integration capabilities
• Provided basic job management tools (submit, stop, monitor)
• System information query tool
• Connection configuration utility

📄 License

Apache License