How to Use the Dagster MCP in Mastra AI

Q: How do I set up human-in-the-loop approvals for Dagster jobs in Mastra AI?

You can use Mastra's requireToolApproval option on sensitive operations. This forces the agent to wait for human confirmation before acting on run metadata.

Trigger conditional workflows and retries on Dagster pipeline failures using Mastra AI agents.

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 Mastra AI

Create your Vinkius account to connect Dagster to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional branching for Dagster failures

If a critical Dagster pipeline run fails, you need more than a generic alert. Mastra AI can monitor your system using `list_runs` and trigger custom recovery workflows when it detects an error. You can write Mastra AI logic that inspects the Dagster run details via `get_run`. If the failure was due to a database timeout, the agent can automatically trigger a pipeline retry or page the on-call engineer.

Automated sensor recovery using Mastra AI

Dagster sensors sometimes stall or miss their triggers. This MCP Server exposes `list_sensors` and `list_schedules` to your Mastra AI agents so they can audit your pipeline automation state. When a Mastra AI agent detects a stalled Dagster sensor, it can run a workflow to notify your Slack channels. You don't have to write custom cron jobs to monitor your pipeline triggers.

Self-healing data asset pipelines

Keep your software-defined Dagster assets fresh without manual intervention. Your Mastra AI agent can call `list_assets` to identify outdated pipeline materializations in your data warehouse. If a Dagster asset is stale, the Mastra AI agent evaluates the dependency graph using the tools. It can then alert the data team or queue up the correct jobs to rebuild the missing partitions.

Setup guide

Set up Dagster MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Dagster tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "dagster-mcp-client",
  servers: {
    "dagster-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Dagster Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Dagster tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Dagster transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the MCP client with the server URL and pass the tools to your agent configuration. The agent can then automatically call `list_runs` or `get_run` during workflow execution.

Yes, Mastra has a built-in workflow engine that handles retries with exponential backoff. If a Dagster MCP tool call fails, the workflow engine retries the call before failing.

You can use Mastra's `requireToolApproval` option on sensitive operations. This forces the agent to wait for human confirmation before acting on run metadata.

Yes, Mastra compiles down to lightweight TypeScript that runs on any cloud provider. You can monitor schedules and jobs without keeping a heavy server running.

All communication between Mastra AI and the MCP Server goes through a zero-trust, ephemeral V8 sandbox. Your job names, asset keys, and run configurations are never stored or exposed to external networks.

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