DolphinScheduler MCP Server logo

DolphinScheduler MCP Server

by ocean-zhc

A Model Context Protocol (MCP) server for Apache DolphinScheduler, allowing AI agents to interact with DolphinScheduler through a standardized protocol. It acts as a bridge between AI models and DolphinScheduler, enabling AI-driven workflow management.

View on GitHub

Last updated: N/A

What is DolphinScheduler MCP Server?

DolphinScheduler MCP provides a FastMCP-based server that exposes DolphinScheduler's REST API as a collection of tools that can be used by AI agents. It serves as an intermediary, translating AI requests into DolphinScheduler actions.

How to use DolphinScheduler MCP Server?

Install the server using pip install dolphinscheduler-mcp. Configure the server using environment variables or command-line arguments, specifying the DolphinScheduler API URL and authentication token. Start the server using the command-line interface (ds-mcp) or the Python API. Use an MCP client to connect to the server and invoke tools.

Key features of DolphinScheduler MCP Server

  • Full API coverage of DolphinScheduler functionality

  • Standardized tool interfaces following the Model Context Protocol

  • Easy configuration through environment variables or command-line arguments

  • Comprehensive tool documentation

Use cases of DolphinScheduler MCP Server

  • AI-driven workflow creation and management

  • Automated scheduling and execution of DolphinScheduler workflows

  • Integration of AI models with DolphinScheduler for intelligent workflow orchestration

  • Dynamic adaptation of workflows based on AI insights

FAQ from DolphinScheduler MCP Server

What is the default port for the MCP server?

The default port is 8089.

How do I authenticate with the DolphinScheduler API?

You need to provide an API token using the DOLPHINSCHEDULER_API_KEY environment variable.

Can I customize the logging level?

Yes, you can set the DOLPHINSCHEDULER_MCP_LOG_LEVEL environment variable.

What kind of tools are available?

Tools are available for Project Management, Process Definition Management, Process Instance Management, and more.

How do I connect to the MCP server from a client?

Use an MCP client library and provide the server's address (e.g., http://localhost:8089/mcp).