How to Use the Dagster MCP in Claude Code

Q: Can Claude Code list all my Dagster assets from the command line?

Yes. Once the server is configured, run claude mcp dagster-mcp listassets. It will output a list of all your software-defined assets, which you can then pipe to other tools like jq for filtering or grep for searching.

Q: What's the Claude Code command for checking Dagster job status?

You'd use the listjobs or listruns tools. For example, claude mcp dagster-mcp listjobs will give you all defined jobs. For their execution status, claude mcp dagster-mcp listruns is what you'll use.

Q: Is there a way to get details for one specific Dagster run with Claude Code?

Yes, use the getrun tool. You'll need the run ID first, which you can get from listruns. Then run claude mcp dagster-mcp getrun --id= to fetch its specific details and logs.

Pipe your Dagster metadata into any script or command-line tool. The perfect headless integration for Claude Code.

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 Claude Code

Create your Vinkius account to connect Dagster to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script Your Pipeline Audits

This is for your cron jobs and CI/CD pipelines. Use Claude Code to call `list_runs --status=FAILED` and pipe the output to a script that pages the on-call engineer. No browser, no UI, just pure automation. You can build some powerful checks this way. For example, a shell script that uses `list_schedules` and `list_sensors` to find any scheduled job that doesn't have a corresponding sensor, flagging potential dead code in your repository.

Monitor Dagster from the Terminal

You don't need a web dashboard. From any SSH session, you can use Claude Code to query this MCP Server. Check on job status with `list_jobs` or see what's currently running with `list_runs`. Chain commands together with standard Unix pipes. `claude mcp dagster-mcp list_runs | grep "my_job" | wc -l` gives you a quick count of how many times a specific job has run. It's simple, fast, and works anywhere you have a terminal.

Integrate with GitOps Workflows

Incorporate pipeline state into your deployment scripts. Before a deploy, have your GitHub Action run a Claude Code command to check the status of critical jobs via `list_runs`. If anything's failing, you can automatically block the release. The `get_run` tool is perfect for post-mortems. When a run fails, a script can automatically call it, grab the error log, and create a new issue in your tracker with all the context. This MCP Server makes that connection.

Setup guide

Set up Dagster MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see dagster-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Dagster transactions." It will automatically discover and invoke the available Dagster tools.

Terminal

claude mcp add --transport http dagster-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "dagster-mcp": {
      "type": "url",
      "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 Claude Code

Connect Claude Code to this MCP Server in your CI environment. Then you can run commands like `claude mcp dagster-mcp list_runs --status=FAILED` as a step in your pipeline. If the command returns any runs, you can fail the build.

Yes. Once the server is configured, run `claude mcp dagster-mcp list_assets`. It will output a list of all your software-defined assets, which you can then pipe to other tools like `jq` for filtering or `grep` for searching.

You'd use the `list_jobs` or `list_runs` tools. For example, `claude mcp dagster-mcp list_jobs` will give you all defined jobs. For their execution status, `claude mcp dagster-mcp list_runs` is what you'll use.

Yes, use the `get_run` tool. You'll need the run ID first, which you can get from `list_runs`. Then run `claude mcp dagster-mcp get_run --id=` to fetch its specific details and logs.

Only metadata about your Dagster instance is accessed: run history, job definitions, asset names, and sensor configurations. Your actual business data is never touched. Each request is handled in a dedicated, single-use V8 isolate on Vinkius, ensuring nothing is persisted.

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