How to Use the Dagster MCP in Vercel AI SDK

Q: How do I stream Dagster run updates using Vercel AI SDK?

Call streamText and pass the tools from createMCPClient. Your AI client will invoke listruns and stream the status updates directly into your UI thread.

Feed real-time Dagster pipeline runs and asset states straight to your Vercel AI SDK frontend without loading spinners.

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 Vercel AI SDK

Create your Vinkius account to connect Dagster to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live asset tracking for Vercel AI SDK UIs

Your users don't want to stare at a stale dashboard when monitoring data pipelines. This MCP Server lets your Vercel AI SDK application pull live data using `list_assets` and feed it directly to your React or Next.js components. Because the Dagster tool results stream straight into the Vercel AI SDK UI, your interface displays asset updates as they occur. You don't have to build custom polling APIs to show what's happening inside your data platform.

Instant pipeline run diagnostics in the browser

When a Dagster asset fails, your Vercel AI SDK chatbot can investigate the failure trace immediately. The streaming agent calls `get_run` and `list_runs` to grab the exact run history from your pipeline. The raw Dagster logs and run details render immediately in the Vercel AI SDK chat interface. Your team gets the context they need to debug pipeline issues without leaving their primary customer tool.

Interactive schedule and sensor controls

Let users inspect automation triggers without opening the Dagster UI. Your Vercel AI SDK frontend can invoke `list_schedules` and `list_sensors` to display active triggers in a clean layout. The Vercel AI SDK handles these Dagster calls on Edge Functions, keeping your page loads fast. Users get a responsive interface to check if a specific pipeline sensor is stalled or if a run schedule is misaligned.

Setup guide

Set up Dagster MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Dagster tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Dagster transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Call `streamText` and pass the tools from `createMCPClient`. Your AI client will invoke `list_runs` and stream the status updates directly into your UI thread.

Yes, the client is fully compatible with Edge runtimes. You can query `list_assets` or `get_run` without cold-start delays or heavy server spin-ups.

The SDK doesn't run the actual pipelines; it queries metadata. It uses `get_run` to check the execution progress and streams that status back to the user interface.

The MCP client throws standard TypeScript errors that you can catch inside your stream loop. Your UI can gracefully degrade or show an error state instead of hanging.

Your pipeline metadata stays secure. The MCP Server only reads run logs, asset definitions, and sensor states, passing them through an encrypted V8 sandbox directly to your Vercel AI SDK backend.

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