Dagster enables AI agents to inspect and operate data orchestration pipelines by exploring assets, jobs, schedules, sensors, and runs. Launch and monitor pipeline executions, inspect logs and failures, review asset dependencies, and troubleshoot data workflows across Dagster deployments.
Hermes is Nous Research's command-line agent. MCP servers are declared in its YAML config and reloaded without a restart.
This guide connects Dagster MCP to Hermes through MewCP, so Hermes can use Dagster MCP's 36 tools, like list_asset_checks, list_runs and get_run, without your Dagster MCP credentials ever reaching the app.
Dagster MCP signs in through managed OAuth. MewCP stores the token encrypted, refreshes it before it expires and injects it only at call time. Your agent never holds it, so it can never leak it.
More apps
TinyFish MCP for running AI-driven browser automation tasks, deep web research, persistent browser login profiles, remote CDP browser sessions, and agentic wallet payments.
Connect to external APIs, webhooks and internet services through standard HTTP requests. Build integrations with virtually any platform that exposes a web-based interface.
Browse the Apify Store to find pre-built scrapers and automation actors, read their input schemas, run them, and pull the resulting datasets. Includes two ready-made web tools: a search-and-scrape browser that queries Google and returns pages as clean Markdown, and a fetcher that renders JavaScript and gets through bot blocking. Also searches Apify and Crawlee documentation.
Search for available domain names and check domain availability using GoDaddy's MCP server. Discover domain ideas for businesses, products, and projects through AI assistants
Other clients
Dagster MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Dagster MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Edit config.yaml in your Hermes config directory (~/.hermes).
Put this under the top-level "mcp_servers:" key.
Run /reload-mcp in Hermes, or start a fresh session. Sign in when the browser window opens.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
List Dagster asset checks by asset key.
List recent Dagster runs, optionally filtered by status or job name.
Get detailed metadata for a single Dagster run.
Get paginated event logs for a Dagster run.
Get metadata about a Dagster Plus deployment.
List the code locations in a Dagster Plus deployment.
List deployments in the organization. Returns either production or branch deployments.
Get metadata and health information for a single asset.
Get paginated assets, optionally filtered by asset key prefix.
Get code location and repository information for a single asset.
Get code location and repository information for multiple assets.
List all alert policies in the current deployment.
Get a single alert policy by ID.
Get the alert policies that currently apply to a specific job.
Get paginated notification history for an alert policy.
Get alert notifications that fired for a run, plus the matching policies.
Get all alert policies as a Dagster config document suitable for editing.
Create or update an alert policy from a Dagster Cloud config document.
List Dagster Issues.
Create a Dagster issue with optional run or asset origin context.
Update an existing Dagster issue.
Link a Dagster run or asset to an Issue.
Remove a link from a Dagster issue.
Delete an alert policy by name.
Launch a new Dagster run for a job, optionally for a subset of its assets.
Materialize an ad hoc selection of assets.
Launch a re-execution of an existing run.
Launch a re-execution of an existing backfill.
Terminate a running Dagster run.
List available metric types for assets.
List available metric types for jobs.
List available metric types for deployments.
Get reporting metrics broken down by asset.
Get reporting metrics broken down by job.
Get reporting metrics broken down by deployment.
Get reporting metrics aggregated across an asset selection.
