How to Use the Dagster MCP in Windsurf

Q: What's the best way to check Dagster sensor status with Windsurf?

The listsensors tool is what you need. Tell Windsurf something like 'Show me all active sensors in Dagster.' It will call the tool and return the current state of your data sensors.

Q: Is it possible to track specific Dagster runs using Windsurf?

Absolutely. You can use the listruns tool to see recent activity. For more detail on a specific one, Windsurf can use getrun with a run ID to pull its complete record, including logs and metadata.

Let Windsurf's Cascade agent manage your Dagster pipelines. Set a goal, like 'check for failed runs,' and watch it happen.

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 Windsurf

Create your Vinkius account to connect Dagster to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check Pipeline Health Instantly

Ask Windsurf to check on your Dagster jobs. Cascade can chain together `list_jobs` and `list_runs` to give you a full picture of what's running, what's finished, and what's failed. No need to click through the Dagster UI. You don't have to prompt every step. Just tell Cascade, 'Audit all scheduled jobs and report on any that failed in the last 24 hours.' It will use `list_schedules` then `list_runs` with the right filters to get the answer.

Audit Assets and Dependencies

Your data pipelines are defined by assets. With this MCP Server, Windsurf can see them all. Use `list_assets` to get a complete inventory of your software-defined assets without leaving your editor. This is great for refactoring. Before you change a model, you can have Cascade pull the asset list and check its downstream dependencies. You'll know exactly what you might break before you even write a line of code.

Diagnose Run Failures Fast

When a run fails, you need details. Instead of digging for logs, just ask Windsurf. It can use `list_runs` to find the failed run ID, then immediately feed that into `get_run` to pull the specific error details. Because Cascade chains these actions, you can build complex diagnostic workflows. 'Find the last failed run for the 'daily_metrics' job and pull its error log.' Cascade handles the two-step process on its own, giving you the answer directly.

Setup guide

Set up Dagster MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Dagster MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Dagster payment history." If connected, Cascade will call the Dagster tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

It connects through this MCP Server. Once you add the server to Windsurf, its Cascade agent automatically discovers the Dagster tools. You can then just ask it to perform tasks like listing jobs or checking runs.

Yes. Just ask Windsurf to 'list all Dagster schedules.' It will use the `list_schedules` tool to fetch a complete list of your configured schedules and their status.

The `list_sensors` tool is what you need. Tell Windsurf something like 'Show me all active sensors in Dagster.' It will call the tool and return the current state of your data sensors.

Absolutely. You can use the `list_runs` tool to see recent activity. For more detail on a specific one, Windsurf can use `get_run` with a run ID to pull its complete record, including logs and metadata.

This server only reads metadata from your Dagster instance. It accesses things like job names, run statuses, asset definitions, and schedule configurations. Vinkius processes this data in an ephemeral, sandboxed environment and never stores it.

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