Apache SeaTunnel MCP server

Interact with SeaTunnel through LLM interfaces like Claude.
Back to servers
Setup instructions
Provider
Ocean ZHC
Release date
Mar 26, 2025
Language
Python
Stats
22 stars

SeaTunnel MCP Server is a tool that enables interaction with SeaTunnel through Large Language Model interfaces like Claude. It provides job management capabilities and system monitoring for SeaTunnel instances through the Model Context Protocol (MCP).

Installation

Prerequisites

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

Setup Instructions

# 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 .

Configuration

Environment Variables

The MCP server uses the following 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

You can view and update connection settings at runtime:

// 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"
  }
}

Running the Server

Start the server with:

python -m src.seatunnel_mcp

Integration 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"
    }
  }
}

Testing with MCP Inspector

npx @modelcontextprotocol/inspector python -m src.seatunnel_mcp

Available Tools

Connection Management

  • get-connection-settings: View current connection configuration
  • update-connection-settings: Update URL and/or API key

Job Management

  • submit-job: Submit a new job with HOCON configuration
  • submit-job/upload: Submit job via configuration file upload
  • submit-jobs: Submit multiple jobs in batch
  • 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

System Monitoring

  • get-overview: Get cluster overview
  • get-system-monitoring-information: Get detailed system monitoring information

Examples

Submitting a Job

{
  "name": "submit-job",
  "arguments": {
    "job_config": "env { job.mode = \"BATCH\" } source { FakeSource { result_table_name = \"fake\" row.num = 10 } } transform {} sink { Console {} }"
  }
}

Stopping a Job

{
  "name": "stop-job",
  "arguments": {
    "job_id": "01234567-89ab-cdef-0123-456789abcdef"
  }
}

Getting Job Information

{
  "name": "get-job-info",
  "arguments": {
    "job_id": "01234567-89ab-cdef-0123-456789abcdef"
  }
}

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "seatunnel" '{"command":"python","args":["-m","src.seatunnel_mcp"],"cwd":"Project root directory"}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "seatunnel": {
            "command": "python",
            "args": [
                "-m",
                "src.seatunnel_mcp"
            ],
            "cwd": "Project root directory"
        },
        "st-mcp-uv": {
            "command": "uv",
            "args": [
                "run",
                "seatunnel-mcp"
            ],
            "env": {
                "SEATUNNEL_API_URL": "http://127.0.0.1:8080"
            }
        },
        "st-mcp-sse": {
            "url": "http://your-server:18080/sse"
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "seatunnel": {
            "command": "python",
            "args": [
                "-m",
                "src.seatunnel_mcp"
            ],
            "cwd": "Project root directory"
        },
        "st-mcp-uv": {
            "command": "uv",
            "args": [
                "run",
                "seatunnel-mcp"
            ],
            "env": {
                "SEATUNNEL_API_URL": "http://127.0.0.1:8080"
            }
        },
        "st-mcp-sse": {
            "url": "http://your-server:18080/sse"
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later