How to Use the Dagster MCP in CrewAI

Q: How do I assign Dagster MCP Server tools to a specific CrewAI agent?

Pass the MCP Server URL to the agent's mcps parameter during initialization. You can restrict tools so only your engineer agent can call getrun or listjobs.

Q: Can multiple CrewAI agents share Dagster context?

Yes, CrewAI agents share memory. If one agent calls listassets, the other agents in the crew can access those asset names to perform their tasks.

Deploy autonomous CrewAI agent teams to monitor Dagster pipelines, debug run errors, and audit assets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dagster MCP to CrewAI

Create your Vinkius account to connect Dagster to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Dagster with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative data pipeline monitoring

Set up a dedicated CrewAI team to watch over your data platform. A researcher agent can use `list_runs` and `list_assets` to collect the latest state of your Dagster pipeline. An analyst agent then reviews those runs to spot performance bottlenecks. They work together in a CrewAI loop, passing Dagster run details back and forth to keep your pipelines healthy.

Autonomous debugging via CrewAI agents

When a Dagster job fails, your CrewAI agents can coordinate to find the root cause. One agent pulls the execution logs using `get_run` while another checks the active configuration via `list_jobs`. The CrewAI team analyzes the failure pattern and drafts a post-mortem report. By sharing memory and context, they can diagnose complex Dagster pipeline errors without human intervention.

Automated schedule and sensor auditing

Use this MCP Server to keep your automation triggers in check. Your CrewAI team can call `list_schedules` and `list_sensors` to verify that all Dagster data loads are running on time. If a Dagster schedule is disabled or a sensor is failing, the CrewAI supervisor agent assigns a task to alert the engineering team. This keeps your data platform running smoothly without constant manual checks.

Setup guide

Set up Dagster MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Dagster tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Dagster Analyst",
    goal="Access and analyze Dagster data via MCP.",
    backstory="Expert analyst with direct Dagster access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Dagster transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Dagster Analyst",
        goal="Access and analyze Dagster data via MCP.",
        backstory="Expert analyst with direct Dagster access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Dagster transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Dagster. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Dagster now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Dagster MCP in CrewAI

Pass the MCP Server URL to the agent's `mcps` parameter during initialization. You can restrict tools so only your engineer agent can call `get_run` or `list_jobs`.

Yes, CrewAI agents share memory. If one agent calls `list_assets`, the other agents in the crew can access those asset names to perform their tasks.

The MCP Server supports stdio, SSE, and Streamable HTTP. For CrewAI setups, using the HTTP transport with the `MCPServerHTTP` class is usually the easiest way to manage connections.

Yes, you can use a tool filter when setting up the client. This ensures your agents only access the specific pipelines and runs they are assigned to monitor.

Your execution history, asset keys, and run logs are entirely protected. The Vinkius MCP sandbox ensures that data retrieved via `list_runs` and `list_assets` is processed ephemerally and never written to persistent disks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript