DolphinScheduler MCP Server
About
A Model Context Protocol (MCP) server for Apache Dolphinscheduler. This provides access to your Apache Dolphinshcheduler RESTful API V1 instance and the surrounding ecosystem.
Details
- Author
- ocean-zhc
- GitHub stars
- 23
- Downloads
- 412
- Categories
- Other
Jump to
- Full coverage of DolphinScheduler REST API functionality
- Standardized tool interfaces following the Model Context Protocol
- Easy configuration via environment variables or CLI arguments
- Comprehensive tool documentation
- Tools for project, process, task, scheduling, resource, datasource, alert, worker, tenant, and user management
- System status monitoring support
Install the Python package via pip install dolphinscheduler-mcp. Configure it using environment variables (e.g., DOLPHINSCHEDULER_API_URL, DOLPHINSCHEDULER_API_KEY) or command-line arguments. Start the server with the ds-mcp --host 0.0.0.0 --port 8089 command or by calling run_server() from the Python API. AI agents can then connect and invoke tools like get-project-list or create-project.
DolphinScheduler MCP Server
A Model Context Protocol (MCP) server for Apache DolphinScheduler, allowing AI agents to interact with DolphinScheduler through a standardized protocol.
Overview
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. The server acts as a bridge between AI models and DolphinScheduler, enabling AI-driven workflow management.
Features
- 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
Installation
pip install dolphinscheduler-mcp
Configuration
Environment Variables
- DOLPHINSCHEDULER_API_URL: URL for the DolphinScheduler API (default: http://localhost:12345/dolphinscheduler)
- DOLPHINSCHEDULER_API_KEY: API token for authentication with the DolphinScheduler API
- DOLPHINSCHEDULER_MCP_HOST: Host to bind the MCP server (default: 0.0.0.0)
- DOLPHINSCHEDULER_MCP_PORT: Port to bind the MCP server (default: 8089)
- DOLPHINSCHEDULER_MCP_LOG_LEVEL: Logging level (default: INFO)
Usage
Command Line
Start the server using the command-line interface:
ds-mcp --host 0.0.0.0 --port 8089
Python API
```python
from dolphinscheduler_mcp.server import run_server
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
