mcpField
M
mcp-dagster: A Dagster MCP Server

mcp-dagster: A Dagster MCP Server

Local
github.com/kyryl-opens-mlCloud & Infra25Updated 81w ago
Repository

About mcp-dagster: A Dagster MCP Server

mcp-dagster is an MCP server for the Dagster data orchestration platform, letting AI agents explore pipelines, monitor runs and manage assets. It is aimed at data engineering teams and serves as a bridge between LLMs and their workflows. The project includes an example OpenAI-based agent and runs over SSE transport.

Key features

  1. 01List repositories, jobs and assets
  2. 02Query recent runs and single run details
  3. 03Launch and terminate job runs
  4. 04Materialize a specific data asset

Use cases

  1. 01Review which assets exist in a Dagster instance
  2. 02Check recent runs and summarize failures
  3. 03Materialize an asset through an agent and view the result

MCP support

This project is an MCP server that exposes Dagster query and operation tools to MCP clients over SSE transport.

#mcp-server#dagster#data-orchestration

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-dagster: A Dagster MCP Server

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. This repository provides an MCP server for interacting with Dagster, the data orchestration platform.

Overview

A Model Context Protocol server that enables AI agents to interact with Dagster instances, explore data pipelines, monitor runs, and manage assets. It serves as a bridge between LLMs and your data engineering workflows.

Read our launch post to learn more.

PyPI version Tests

Components

Tools

The server implements several tools for Dagster interaction:

  • list_repositories: Lists all available Dagster repositories
  • list_jobs: Lists all jobs in a specific repository
  • list_assets: Lists all assets in a specific repository
  • recent_runs: Gets recent Dagster runs (default limit: 10)
  • get_run_info: Gets detailed information about a specific run
  • launch_run: Launches a Dagster job run
  • materialize_asset: Materializes a specific Dagster asset
  • terminate_run: Terminates an in-progress Dagster run
  • get_asset_info: Gets detailed information about a specific asset

Configuration

The server connects to Dagster using these defaults:

  • GraphQL endpoint: http://localhost:3000/graphql
  • Transport: SSE (Server-Sent Events)

Quickstart

Running the Example
  1. Start the Dagster instance with your pipeline:
uv run dagster dev -f ./examples/open-ai-agent/pipeline.py
  1. Run the MCP server with SSE transport:
uv run examples/open-ai-agent/run_sse_mcp.py
  1. Start the agent loop to interact with Dagster:
uv run ./examples/open-ai-agent/agent.py
Example Interactions

Once the agent is running, you can ask questions like:

  • "What assets are available in my Dagster instance and what do they do?"
  • "Can you materialize the continent_stats asset and show me the result?"
  • "Check the status of recent runs and provide a summary of any failures"
  • "Create a new monthly aggregation asset that depends on continent_stats"

The agent will use the MCP server to interact with your Dagster instance and provide answers based on your data pipelines.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.