How to Use the Dagster MCP in Pydantic AI

Run type-safe pipeline monitoring using Pydantic AI 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 Pydantic AI

Create your Vinkius account to connect Dagster to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Dagster Run Details in Pydantic AI

The `get_run` and `list_runs` tools return structured execution metadata through the MCP Server, which Pydantic AI validates against strict schemas at runtime. If the Dagster API returns unexpected fields, your python code catches the error immediately. Malformed dates and hallucinated IDs never reach your internal monitoring tools. You get clean, type-safe Python objects instead of raw, untrusted JSON payloads.

Audit Assets and Jobs with Zero Silent Failures

The `list_assets` and `list_jobs` tools let your agent map out your data pipelines without risk. Your Pydantic AI agent parses the asset lists and job configurations, ensuring every field matches your exact data models. When an asset key format changes in your pipeline, the agent fails loudly. You catch schema drift in your data platform before your agent makes decisions based on outdated information.

Check Pipeline Schedules and Sensors Safely

The `list_schedules` and `list_sensors` tools expose active triggers and cron schedules to your type-safe agent. The agent reads this metadata to verify if your data pipelines are running on time. Pydantic AI works with any LLM provider here, handling the tool calls reliably. The agent checks sensor states, catches delays, and raises alerts using validated data structures.

Setup guide

Set up Dagster MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "dagster-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Dagster tools.",
)

result = await agent.run("List recent Dagster transactions")
print(result.output)

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 Pydantic AI

Use the MCPToolset class pointing to your Vinkius HTTP URL. Pass this object into the toolsets parameter when initializing your Pydantic AI Agent.

It guarantees type safety at runtime. If the pipeline metadata doesn't match your schemas, the agent raises a validation error instead of passing bad data down the line.

Yes, you can connect the framework to your hosted Vinkius endpoint using either streamable HTTP or SSE transports depending on your network setup.

No, Vinkius hosts the server for you. Your agent connects to a managed endpoint, meaning you don't have to manage any local node or python processes.

Every request runs inside an isolated, zero-trust V8 sandbox. Your credentials and pipeline metadata are processed ephemerally, ensuring nothing is cached or stored.

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