How to Use the Dagster MCP in Cursor

Q: How do I configure the Dagster MCP Server in Cursor?

You add the configuration details to your .cursor/mcp.json file in your project root. Once configured, enable Agent mode in the chat panel to let the editor invoke the pipeline tools.

Q: Does the Dagster MCP integration work with Cursor global settings?

Yes, you can define the server in your global /.cursor/mcp.json file. This makes the tools available across all your local repositories and data workspaces.

Q: What pipeline data does Cursor send to external LLMs?

Only the pipeline metadata returned by tools like listjobs or getrun is sent to the LLM. Your raw database records, warehouse credentials, and actual data payloads are never accessed or transmitted by this tool.

Debug failing Dagster runs and check asset schemas directly inside your Cursor editor.

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 Cursor

Create your Vinkius account to connect Dagster to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write pipeline code using Cursor and Dagster

Run `list_assets` inside Cursor to pull your live asset catalog directly into your active workspace. Cursor uses this real-time Dagster metadata to write accurate asset definitions directly inside your Cursor editor.

Debug broken jobs inside the editor

Use `get_run` or `list_runs` in Cursor to fetch the execution logs of your latest pipeline failure. Debugging is simplified as your agent analyzes the actual Dagster run traceback alongside your open Python files in Cursor.

Track job schedules while coding

Query `list_schedules` and `list_sensors` inside Cursor to quickly check which triggers are currently active. By comparing your active Dagster sensors with the configuration code open in Cursor, you spot deployment mismatches instantly.

Setup guide

Set up Dagster MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Dagster MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Dagster transactions." If the MCP tools are loaded correctly, Cursor will call the Dagster tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "dagster-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

You add the configuration details to your `.cursor/mcp.json` file in your project root. Once configured, enable Agent mode in the chat panel to let the editor invoke the pipeline tools.

No, this server focuses on monitoring and metadata retrieval. Cursor can call `list_runs` or `get_run` to inspect what happened, but it cannot initiate or trigger new pipeline executions.

Yes, you can define the server in your global `~/.cursor/mcp.json` file. This makes the tools available across all your local repositories and data workspaces.

No, your authentication tokens are managed securely by Vinkius. The editor only communicates with the secure endpoint, keeping your API keys out of your local configuration files.

Only the pipeline metadata returned by tools like `list_jobs` or `get_run` is sent to the LLM. Your raw database records, warehouse credentials, and actual data payloads are never accessed or transmitted by this tool.

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