Dagster Mcp
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).
Overview
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:
{
"mcpServers": {
"dagster": {
"command": "uvx",
"args": ["dagster-mcp"],
"env": {
"DAGSTER_URL": "http://localhost:3000"
}
}
}
}
Published on https://pypi.org/project/dagster-mcp/. MIT licensed.
Server Config
{
"mcpServers": {
"dagster": {
"command": "uvx",
"args": [
"dagster-mcp"
],
"env": {
"DAGSTER_URL": "http://localhost:3000"
}
}
}
}Project Info
Created At
2 months agoUpdated At
2 months agoAuthor Name
fabdendevStar
-Language
-License
-Recommend Servers
View AllMcp Server Chatsum
@chatmcp
summarize chat message
typescript
a year ago
Test
@modelcontextprotocol
test
6 months ago