MCP For Claude Marketplace
Dagster

Dagster MCP Connector for Claude

A+

Orchestrate data pipelines via Dagster — monitor jobs, track runs, manage software-defined assets, and audit schedules directly from any AI agent.

6 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Dagster (Plus or open-source) instance to any AI agent and take full control of your data orchestration and asset management through natural conversation.

What you can do

  • Job Orchestration — List and audit all data jobs available in your Dagster server to understand active pipeline boundaries
  • Run Monitoring — Fetch chronological history of recent job runs and retrieve detailed status and execution logs for specific run IDs
  • Asset Tracking — Enumerate software-defined assets to identify data dependencies and verify physical storage mappings
  • Schedules & Sensors — List all configured job schedules and active sensors listening for external events to audit automation triggers
  • Environment Audit — Identify deployment boundaries and verify instance connectivity across Dagster Plus or self-hosted clusters

How it works

  1. Subscribe to this server
  2. Enter your Dagster URL and User API Token (found in Deployment Settings > Tokens)
  3. Start managing your data pipelines from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Data Engineers — monitor pipeline health and identify failed runs without leaving the chat or IDE
  • Analytics Engineers — track software-defined assets and verify data freshness in real-time
  • Data Platform Teams — audit job schedules and sensor configurations across organizational deployments
  • SREs — monitor Dagster agent health and verify instance connectivity through natural language
data-orchestrationdata-pipelinesworkflow-automationobservabilitydata-engineeringasset-management

6 tools expose this connector's capabilities to your AI agent.

list_schedules

List all schedules from Dagster

list_runs

List recent runs from Dagster

list_sensors

List all sensors from Dagster

get_run

Get run details from Dagster

list_assets

List all assets from Dagster

list_jobs

List all jobs from Dagster

See how to talk to your AI agent using Dagster.

List all jobs in my Dagster deployment

I found 5 jobs in your deployment including 'daily_etl_job', 'ml_training_pipeline', and 'sensor_triggered_sync'. Which one would you like to audit for recent runs?

Show me the status of the last 5 runs

Here are the last 5 runs. The most recent (ID: 123) for 'daily_etl_job' finished with status 'Success'. Run 121 failed. Would you like to see the error logs for the failed run?

What assets are currently defined in my project?

I found 12 software-defined assets including 'raw_customer_data', 'cleaned_sales_table', and 'monthly_metrics_view'. I can provide the materialization history for any of these assets.

Yes. Use the 'list_assets' tool. Your agent will retrieve all software-defined assets, allowing you to identify data dependencies and verify physical storage mappings within your pipelines.

Related Connectors

Datadog

Datadog MCP

11 tools Official

Monitor applications via Datadog — query performance metrics, search logs, and list active monitors directly from any AI agent.

A+ View details →
Sumo Logic

Sumo Logic MCP

9 tools Official

Connect your AI to Sumo Logic. Orchestrate log searches, monitor active collectors, and analyze system events efficiently.

A+ View details →
LangSmith

LangSmith MCP

3 tools Official

Observability and evaluation platform for LLM applications — monitor traces, debug agent runs, and track performance metrics across your AI stack.

A+ View details →
Logstash (Server-side Log Pipeline API)

Logstash (Server-side Log Pipeline API) MCP

6 tools Official

Monitor and manage Logstash instances — check node health, inspect pipeline statistics, and troubleshoot hot threads directly from any AI agent.

A+ View details →