$ loading_
Connect to Dagster to inspect pipelines, monitor runs, and manage assets.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-dagster" yet — see the docs or source repo.
Connect to my Dagster instance, find failed pipeline runs in the last 24 hours, summarize failed jobs, error messages, and likely causes, then prioritize troubleshooting suggestions.
A failure overview with job names, error summaries, impact, and troubleshooting recommendations.
Explore the assets in this Dagster project, map upstream and downstream dependencies for key data assets, and clearly explain which assets are most critical and which chains are most fragile.
A data asset dependency summary highlighting critical assets, dependency paths, and potential risk points.
Review recent run status for all major data pipelines in the current Dagster instance, report success rates, average duration, and anomaly trends, and identify pipelines that need attention.
A pipeline health report with success rates, duration metrics, anomaly trends, and priority watch items.
Orchestrate multiple AI agents in real time and monitor tasks and artifacts.
Build, validate, and monitor data pipelines from natural language requests.
Orchestrate AI agent workflows with dependencies, parallel execution, and failure policies.
Use AI to search Datadog logs, traces, metrics, and correlate incidents.
Connect to Apache Airflow to inspect workflows, trigger DAGs, and monitor health.
Let your AI agent manage PagerDuty alerts, incidents, and on-call workflows.