seatunnel-mcp

A Model Context Protocol (MCP) server for interacting with SeaTunnel through LLM interfaces like Claude.

To help you better understand the features and usage of SeaTunnel MCP, we provide a video demonstration. Please refer to the link below or directly check the video file in the project documentation directory.

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

Tip: If the video does not play directly, make sure your device supports MP4 format and try opening it with a modern browser or video player.

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

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

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

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

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

The server provides tools to view and update connection settings at runtime:

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

Example usage through MCP:

// 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"
  }
}

The server provides tools to submit and manage SeaTunnel jobs:

• submit-job: Submit a new job with job configuration
• submit-jobs: Submit multiple jobs in batch
• stop-job: Stop a running job
• get-job-info: Get detailed information about a specific job
• get-running-jobs: List all currently running jobs
• get-finished-jobs: List all finished jobs by state (FINISHED, CANCELED, FAILED, etc.)

python -m src.seatunnel_mcp

To use this with Claude Desktop, add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "seatunnel": {
      "command": "python",
      "args": ["-m", "src.seatunnel_mcp"],
      "cwd": "Project root directory"
    }
  }
}

npx @modelcontextprotocol/inspector python -m src.seatunnel_mcp

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

• submit-job: Submit a new job with configuration in HOCON format
• submit-job/upload: submit job source upload configuration file
• submit-jobs: Submit multiple jobs in batch, directly passing user input as request body
• stop-job: Stop a running job with optional savepoint
• get-job-info: Get detailed information about a specific job
• get-running-jobs: List all currently running jobs
• get-running-job: Get details about a specific running job
• get-finished-jobs: List all finished jobs by state

• get-overview: Get an overview of the SeaTunnel cluster
• get-system-monitoring-information: Get detailed system monitoring information

• New Feature: Added submit-jobs and submit-job/upload tool for batch job submission and Document submission operations
  • Allows submitting multiple jobs at once with a single API call
  • Input is passed directly as the request body to the API
  • Supports JSON format for job configurations
  • Allow submission of jobs based on documents

• Initial release with basic SeaTunnel integration capabilities
• Job management tools (submit, stop, monitor)
• System monitoring tools
• Connection configuration utilities

Apache License