How to Use the Dagster MCP in OpenAI Agents SDK

Build production-grade data pipeline monitors with OpenAI Agents SDK and the Dagster MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Dagster to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Dagster Runs Safely in OpenAI Agents SDK

The `list_runs` and `get_run` tools let your OpenAI agent inspect execution state directly from your pipeline orchestrator. Your agent pulls raw execution IDs, run times, and step-by-step logs to diagnose failures on the fly. Because OpenAI's SDK enforces strict guardrails, the agent cannot execute these MCP tools without explicit approval. You set the execution boundaries in Python, and the agent queries the Dagster API safely inside those limits.

Audit Pipeline Assets and Schedules

The `list_assets` and `list_schedules` tools expose your software-defined assets and cron rules to the agent. It reads the current asset graph to find out which tables are stale or which schedules missed their window. Pipeline metadata feeds directly into your multi-agent system. If an asset is broken, a specialized cleanup agent takes over the context and alerts the on-call engineer with the exact asset key.

Inspect Dagster Jobs and Sensors

The `list_jobs` and `list_sensors` tools give your agent a clear view of your active pipelines and event triggers. It checks if a sensor is stuck or if a specific job failed to trigger after an upstream database update. Every call goes through OpenAI's tracing dashboard. You watch the agent select these tools in real-time, verifying that it only queries metadata without messing up your production pipeline state.

Setup guide

Set up Dagster MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Dagster tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dagster tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dagster tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Dagster Agent",
            instructions="You have access to Dagster tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the OpenAI agents library and register the Vinkius MCP Server endpoint. Pass the server URL to your agent's configuration block to auto-discover all six tools instantly.

Yes, you control this at the SDK level during initialization. Filter the tool list before passing it to the Agent constructor to block specific tools like schedule checking.

You should set the cache tool parameter to true in your python setup. This stops the agent from making redundant HTTP calls to fetch the tool definitions on every turn.

You write one agent to watch runs and another to audit assets. When a run fails, the first agent hands the context over to the asset specialist to find the root cause.

Your run logs and asset names stay isolated. Vinkius runs the server in an ephemeral V8 sandbox that destroys itself after the execution finishes, preventing any persistent data leaks.

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