• ACTIVE
  • STALLED
  • MISMATCH
  • HUMAN

How to audit pipeline automation with your AI

Connect Dagster to your AI client to monitor your orchestration layer. Once connected, your agent can inspect your automation state in real time.

Ask AI about this page

Short answer

How can I check if my Dagster schedules and sensors are working?

Your AI uses the Dagster MCP to pull a list of all active schedules and sensors. It then compares their current status against your expectations to find stalled or inactive workflows.

Audit outcomes

Where your audit results land.

The AI categorizes the state of your Dagster environment into these four areas.

ACTIVE

Healthy workflows

The AI confirms that your schedules and sensors are active and running. You get a clear view of your operational state.

STALLED

Inactive automation

The AI identifies sensors or schedules that aren't triggering. It flags these so you can see why the event loop stopped.

MISMATCH

Configuration drift

The AI spots discrepancies between your intended automation setup and what is actually running. It highlights these gaps for you.

HUMAN

Manual intervention

The AI identifies complex failures that require a person to fix. It provides the context you need to jump into the Dagster UI.

The workflow

What your AI does when <the thing arrives>.

The AI acts as a bridge between your natural language questions and the Dagster orchestration engine.

  1. Fetch automation list

    The AI pulls a complete list of all defined schedules and sensors from your Dagster instance.

    list_scheduleslist_sensors

  2. Analyze status

    The agent looks at the metadata for each item to see if they are currently active or if they have failed to trigger.

    list_scheduleslist_sensors

  3. Identify gaps

    The AI compares the list of running automations against your specific questions about what should be happening.

    list_scheduleslist_sensors

  4. Report findings

    The AI summarizes which workflows are healthy and which ones need your attention.

    list_scheduleslist_sensors

Try it

Copy these to start.

Use these prompts to begin your audit.

Starting points

Swap out the specific names like 'daily_sync_sensor' for your actual Dagster resource names.

Dagster Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_9Cla5bbOzNXXdswxQ5yhHdcbDLhh8oRbE80hiC24/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Dagster capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "dagster-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_9Cla5bbOzNXXdswxQ5yhHdcbDLhh8oRbE80hiC24/mcp"
    }
  }
}
Copy into chat04

  • List all my active Dagster sensors and tell me if any are inactive.

  • Check the status of the 'nightly_etl_schedule' to see if it's running.

  • Are there any sensors in my Dagster instance that haven't triggered recently?

  • Give me a summary of all my current schedules and their operational status.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Dagster once, then ask.

You only need to link your Dagster instance once. After that, your AI client can handle all your status checks through the Vinkius-hosted MCP.

Connect Dagster to your AI

FAQ

How this task behaves

  • 01

    Can the AI fix a broken sensor?

    No. The AI can only read the status of your sensors and schedules. You must manually fix any issues in Dagster.

  • 02

    Can the AI create new schedules?

    No. This MCP is limited to listing existing schedules and sensors to audit their state.

  • 03

    Does the AI see my data payloads?

    No. The AI only sees the metadata and status of the schedules and sensors themselves.

  • 04

    How often does the AI check the status?

    The AI only checks the status when you ask it a question. It does not monitor your pipelines in the background.

  • 05

    Can I use this with Cursor?

    Yes. Any MCP-compatible client like Cursor, Claude, or Windsurf can use this once you connect it via Vinkius.

  • More questions about Dagster? The Connector page answers them. See everything the Dagster Connector can do

Connect Dagster to Claude, Cursor, ChatGPT & more