SeaTunnel
A Model Context Protocol server that enables interaction with Apache SeaTunnel through LLM interfaces, allowing users to manage jobs, monitor system information, and configure connections through natural language.
What is SeaTunnel?
SeaTunnel is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that enables interaction with apache seatunnel through llm interfaces, allowing users to manage jobs, monitor system information, and configure connections through natura...
A Model Context Protocol server that enables interaction with Apache SeaTunnel through LLM interfaces, allowing users to manage jobs, monitor system information, and configure connections through natural language.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol server that enables interaction wit
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx seatunnel-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use SeaTunnel
The SeaTunnel MCP Server connects AI assistants to a running Apache SeaTunnel cluster through its REST API, enabling natural language management of data pipeline jobs, cluster monitoring, and connection configuration. It exposes tools for submitting HOCON-configured jobs, stopping running jobs with optional savepoints, querying job status, and retrieving system monitoring metrics — all without needing to interact with the SeaTunnel REST API directly. Data engineers who operate Apache SeaTunnel pipelines and want to manage them conversationally, trigger jobs from their AI assistant, or monitor cluster health through natural language queries will find this server a practical operations interface.
Prerequisites
- Python 3.12 or later
- A running Apache SeaTunnel instance (the MCP server connects to its REST API, default port 8090)
- pip or a Python virtual environment for installing the server
- An MCP client such as Claude Desktop or any agent supporting the Model Context Protocol
- Node.js (optional, for testing with the MCP Inspector)
Clone the repository
Download the SeaTunnel MCP Server source code to your local machine.
git clone https://github.com/ocean-zhc/seatunnel-mcp.git
cd seatunnel-mcpCreate a virtual environment and install dependencies
Set up a Python virtual environment and install the server package in editable mode.
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
pip install -e .Verify your SeaTunnel instance is running
Confirm that your Apache SeaTunnel cluster is accessible at its REST API URL. The default is http://localhost:8090. Test connectivity with a curl call.
curl http://localhost:8090/hazelcast/rest/maps/system-monitoring-informationAdd the server to your MCP client configuration
Open claude_desktop_config.json (or your MCP client's config) and add the seatunnel server block. Set SEATUNNEL_API_URL to your SeaTunnel REST API endpoint and optionally SEATUNNEL_API_KEY if authentication is enabled.
{
"mcpServers": {
"seatunnel": {
"command": "/absolute/path/to/seatunnel-mcp/.venv/bin/python",
"args": ["-m", "src.seatunnel_mcp"],
"cwd": "/absolute/path/to/seatunnel-mcp",
"env": {
"SEATUNNEL_API_URL": "http://localhost:8090",
"SEATUNNEL_API_KEY": "your_api_key_if_required"
}
}
}
}Restart your MCP client and test the connection
Restart Claude Desktop or your chosen MCP client. Ask the AI to get the SeaTunnel cluster overview to confirm the server is connected.
SeaTunnel Examples
Client configuration (Claude Desktop)
Add this to claude_desktop_config.json, replacing paths and the API URL with your real values.
{
"mcpServers": {
"seatunnel": {
"command": "/Users/yourname/seatunnel-mcp/.venv/bin/python",
"args": ["-m", "src.seatunnel_mcp"],
"cwd": "/Users/yourname/seatunnel-mcp",
"env": {
"SEATUNNEL_API_URL": "http://localhost:8090"
}
}
}
}Prompts to try
Use these prompts with your MCP client to manage and monitor your Apache SeaTunnel cluster.
- "Show me the current SeaTunnel cluster overview and status."
- "List all currently running SeaTunnel jobs."
- "Show me the finished jobs and their completion status."
- "Get the system monitoring information for the SeaTunnel cluster."
- "Stop job with ID 12345 and create a savepoint."
- "What is the current connection configuration for the MCP server?"Troubleshooting SeaTunnel
Connection refused or cannot reach SeaTunnel REST API
Verify Apache SeaTunnel is running and the REST API is enabled. The default port is 8090; check your SeaTunnel configuration (seatunnel.yaml) to confirm the REST API plugin is activated and the port matches SEATUNNEL_API_URL. Test directly with 'curl http://localhost:8090/hazelcast/rest/maps/system-monitoring-information'.
Python module not found or import errors when starting the server
Ensure you ran 'pip install -e .' from within the project directory with the virtual environment activated. The command in your MCP config should point to the Python binary inside the virtual environment (.venv/bin/python), not the system Python, to ensure all dependencies are available.
Job submission fails with a configuration error
SeaTunnel jobs are submitted as HOCON configuration strings. Verify the job configuration is valid HOCON syntax and references connector plugins that are installed on your SeaTunnel cluster. Check the SeaTunnel logs at the cluster side for detailed error messages about missing connectors or configuration issues.
Frequently Asked Questions about SeaTunnel
What is SeaTunnel?
SeaTunnel is a Model Context Protocol (MCP) server that model context protocol server that enables interaction with apache seatunnel through llm interfaces, allowing users to manage jobs, monitor system information, and configure connections through natural language. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install SeaTunnel?
Follow the installation instructions on the SeaTunnel GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with SeaTunnel?
SeaTunnel works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is SeaTunnel free to use?
Yes, SeaTunnel is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
SeaTunnel Alternatives — Similar Data Science & ML Servers
Looking for alternatives to SeaTunnel? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up SeaTunnel in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use SeaTunnel?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.