Queries Dagster+ assets, runs and pipeline health through Dagster's hosted MCP server: read run logs, launch runs and manage alert policies. For data engineering teams.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with Dagster+ MCP connected:
- Runs & Run Logs
Use Dagster+ MCP to view Dagster+ runs: ‹what you need›
- Assets
Use Dagster+ MCP to view Dagster+ assets: ‹what you need›
- Alert Policies
Use Dagster+ MCP to view alert policies in your Dagster+ deployment: ‹what you need›
Connect it over MCP
{
"mcpServers": {
"dagster-mcp": {
"url": "https://mcp.agent.dagster.cloud/mcp"
}
}
}claude mcp add --transport http dagster-mcp https://mcp.agent.dagster.cloud/mcp
In Grok, ChatGPT and other assistants, add a custom connector with the address https://mcp.agent.dagster.cloud/mcp (how, step by step).
It may ask you to sign in to Dagster Labs or for a key when you add it; the setup guide says which.
Setup guide: dagster.io/docs/getting-started/ai-tools/dagster-mcp
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- MCP
- Auth
- OAuth 2.0
- Skills
- 5
Skills
Runs & Run Logs
Views, launches and terminates Dagster+ runs and reads their run logs and Insights metrics to debug failing pipelines.
Assets
Views Dagster+ assets with their Insights metrics, launches assets, and deletes assets in your Dagster+ deployment.
Alert Policies
Views, creates, updates and deletes alert policies in your Dagster+ deployment from inside an AI session.
Dagster+ Issues
Views, creates and updates Dagster+ Issues so problems found in pipelines are tracked inside your deployment.
Deployments
Views Dagster+ deployments and their Insights metrics and deletes deployments you no longer need.
