How to Use the Dagster MCP in LangChain

Run complex, multi-step Dagster pipeline diagnostics in your LangChain graphs using this 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 LangChain

Create your Vinkius account to connect Dagster to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace Dagster pipeline failures through LangChain

The `get_run` tool pulls raw Dagster execution logs and error states directly into your active LangChain reasoning chain. Your LangChain agent inspects failing Dagster steps, catches the traceback, and passes that context to the next node in your graph. By feeding these Dagster run details into LangSmith, you trace exactly how your LangChain agent diagnosed the pipeline break. You see the latency of the Dagster tool call and the raw JSON payload in your LangChain traces.

Audit Dagster assets and jobs in LangChain

The `list_assets` tool exposes your software-defined Dagster assets directly to your LangChain agent's context window. Your LangChain agent matches these Dagster assets against your database schemas to find missing upstream dependencies. Combine this with `list_jobs` to verify which Dagster pipelines are active in your LangChain workflow. Your LangChain agent chains these calls to map out your entire Dagster graph and spot inactive pipelines.

Automate Dagster schedule checks in LangChain loops

The `list_schedules` and `list_sensors` tools let your LangChain agent audit your Dagster triggers without you leaving the terminal. The LangChain agent reads the Dagster schedule definitions, checks if they are running, and flags misconfigured cron expressions. Because LangChain supports over 500 integrations, you can feed these Dagster schedule states straight into Slack. The LangChain agent handles the decision logic, deciding when to alert you based on the Dagster sensor status.

Setup guide

Set up Dagster MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Dagster tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "dagster-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Dagster transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with the Vinkius URL for Dagster. This lets your LangChain agent fetch all six Dagster tools instantly.

No, this Dagster server is read-only for safety. Your LangChain agent uses `list_runs` and `get_run` to diagnose Dagster issues, but it cannot trigger runs.

The LangChain adapter passes tool execution directly to your chain, so you manage Dagster rate limits at your provider. LangSmith tracks every `list_assets` call so you spot excessive Dagster polling.

Yes, you can pass the tools from this MCP server alongside database tools to your LangChain agent. This lets the agent verify Dagster asset metadata against your warehouse schema in one run.

Yes, Vinkius processes your Dagster run details and asset metadata inside an isolated, ephemeral V8 sandbox. Your Dagster credentials never leave the secure LangChain execution path.

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