Dagster Mcp
About
Monitor and operate Dagster instances with AI agents. 19 tools for runs, assets, jobs, schedules, sensors, and instance health. Supports multi-environment, cross-version compatibility, and write operations (launch, terminate, reload).
Details
- Author
- fabdendev
- Downloads
- 313
- Categories
- Other
Jump to
- 19 tools across runs, assets,
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Dagster McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install the package from PyPI and add it to your MCP client configuration using the uvx command. Set the DAGSTER_URL environment variable to point to your Dagster instance (e.g., http://localhost:3000).
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"dagster mcp": {
"dagster": {
"command": "uvx",
"args": [
"dagster-mcp"
],
"env": {
"DAGSTER_URL": "http://localhost:3000"
}
}
}
}
}McpServers
{
"dagster": {
"command": "uvx",
"args": [
"dagster-mcp"
],
"env": {
"DAGSTER_URL": "http://localhost:3000"
}
}
}An MCP server that wraps the Dagster GraphQL API, giving AI agents full visibility and control
over running Dagster instances — like an SRE for your data pipelines.
## Features
- 19 tools across runs, assets, jobs, schedules/sensors, instance health, and write
operations
- Multi-environment support — monitor prod, staging, and dev from one server
- Cross-version compatible — auto-detects Dagster schema via introspection
- Read-only by default — write tools (launch, terminate, reload) are opt-in
- Zero config — works with self-hosted and Dagster Cloud
## Quick start
Install from PyPI and add to your MCP client:
``json``
{
"mcpServers": {
"dagster": {
"command": "uvx",
"args": ["dagster-mcp"],
"env": {
"DAGSTER_URL": "http://localhost:3000"
}
}
}
}
Published on https://pypi.org/project/dagster-mcp/. MIT licensed.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
