What are the configuration requirements?

You must set `DOLPHINSCHEDULER_API_URL` (default `http://localhost:12345/dolphinscheduler`) and `DOLPHINSCHEDULER_API_KEY` for authentication. The server host, port, and log level can also be configured.

How do I start the server?

Run the `ds-mcp` command with optional `--host` and `--port` arguments, or use the `run_server()` function in Python.

What credentials does it need?

It reads `DOLPHINSCHEDULER_API_URL`, `DOLPHINSCHEDULER_API_KEY`, `DOLPHINSCHEDULER_MCP_HOST` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

DolphinScheduler MCP Server

A Model Context Protocol (MCP) server for Apache Dolphinscheduler. This provides access to your Apache Dolphinshcheduler RESTful API V1 instance and

Local serverstdioPython

What is the DolphinScheduler MCP Server?

A Model Context Protocol (MCP) server for Apache Dolphinscheduler. This provides access to your Apache Dolphinshcheduler RESTful API V1 instance and the surrounding

What you get

A Model Context Protocol (MCP) server for Apache DolphinScheduler, allowing AI agents to interact with DolphinScheduler through a standardized protocol.

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.

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

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the DolphinScheduler MCP Server

{
  "mcpServers": {
    "dolphinscheduler": {
      "command": "uvx",
      "args": ["dolphinscheduler-mcp"],
      "env": {
        "DOLPHINSCHEDULER_API_URL": "your-value",
        "DOLPHINSCHEDULER_API_KEY": "your-value",
        "DOLPHINSCHEDULER_MCP_HOST": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

Variable	Description	Required
DOLPHINSCHEDULER_API_URL	Endpoint or connection string the server talks to.	Yes
DOLPHINSCHEDULER_API_KEY	Credential the server authenticates with.	Yes
DOLPHINSCHEDULER_MCP_HOST	Endpoint or connection string the server talks to.	Optional

Frequently asked questions

It provides a standardized MCP interface so AI agents can interact with Apache DolphinScheduler’s REST API without custom integration code.

Alternatives to the DolphinScheduler MCP Server

Memory

Official

Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.

Knowledge & MemoryTypeScript★ 63.0k

Sequential Thinking

Official

A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.

Knowledge & MemoryTypeScript★ 63.0k

Iac Memory

Provides persistent memory storage for Infrastructure-as-Code (IaC) components, focusing on version tracking and relationship mapping.

Knowledge & MemoryPython★ 5

Blck Alpaca Knowledge Base

Public MCP server for the Blck Alpaca knowledge base: SEO, GEO (generative engine optimization), AI agents and marketing automation. Read-only, no authentication, German, English and Slovak.

Social Media & MarketingRemote

memplato

Every AI conversation starts from zero. MemPlato fixes that — it's a persistent memory layer for AI assistants, running entirely on your own device. Your data never leaves your phone.

Knowledge & Memory

Arxiv Search MCP

Once installed in your agent's environment, you can load it with the settings in [`sample_settings.json`](./sample_settings.json).

Knowledge & MemoryPython