Dagster MCP
UnclaimedMCP server that wraps the Dagster GraphQL API — monitor and operate runs, assets, schedules, sensors, and backfills from any MCP client
Set up this server
01 / Choose your client
02 / Before you connect
Authentication is not specified. Check the project instructions before connecting.
Project instructions03 / Add the configuration
claude mcp add --transport stdio 'dagster-mcp' -- 'uvx' 'dagster-mcp'04 / Check it in your client
Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
27 of 27 tools
Documented tools (27)
From project documentation. A server handshake does not verify each tool’s description or behavior.
backfill_assets
Launch a partition backfill by asset selection with optional run config; respects each asset's BackfillPolicy server-side
get_asset_details
Get description, upstream/downstream dependencies, partitions, latest materialization
get_asset_health
Consolidated health view — staleness, freshness policy, last run status (works with single asset or entire group)
get_instance_status
Start here — global health: daemon status, queued run count, code location errors
get_recent_materializations
Get materialization history with metadata for an asset
get_run_failure_summary
Consolidated failure diagnosis — failed steps, root cause error, step durations, and suggestions in one call
get_run_logs
Get structured log events with pagination and optional level filtering (ERROR, WARNING, INFO); EngineEvent events include metadataEntries
get_run_stats
Get per-step execution stats: timing, materializations, expectation results
get_run_status
Get status, config, tags, and run lineage (re-execution chain via rootRunId/parentRunId)
get_runs
List recent runs, filter by job name and/or status
get_tick_history
Tick-by-tick history for a schedule or sensor — essential for detecting silent failures. Accepts optional repositoryname / locationname to disambiguate a name shared by several code locations
launch_job
Launch a named job; assetkeys remains supported for compatibility and is sent through GraphQL assetSelection, but the two-step asset workflow is preferred
launch_job_with_partitions
Launch a partitioned job for one or more partition keys; creates a backfill (supports fromfailure to retry only failed steps)
list_backfills
List recent backfills with status and partition progress
list_code_locations
List all code locations and their load status
list_jobs
List jobs across code locations, optionally filtered by exact repositoryname and/or locationname (use to find names for launchjob)
list_schedules
List schedules with status (RUNNING/STOPPED), cron, target job, next tick
list_sensors
List sensors with status and target jobs
materialize_assets
Launch concrete, unpartitioned asset keys with run config and tags; infers one compatible repository/job, includes compatible checks, and expands required non-subsettable multi-asset neighbors
reload_code_location
Reload a code location after deploy
resolve_asset_selection
Resolve key/group/tag/kind/owner predicates, wildcards, boolean logic, roots/sinks, and lineage traversal into concrete asset keys without launching anything
search_assets
Discover assets by key prefix or group name
start_schedule
Start (enable) a schedule so it launches runs on its cron
start_sensor
Start (enable) a sensor so it resumes evaluating
stop_schedule
Stop (disable) a schedule — persists across restarts; does not terminate in-flight runs
stop_sensor
Stop (disable) a sensor — the fix for a runaway or erroring sensor found via gettickhistory
terminate_run
Stop a stuck or runaway run
Tool change history
FAQ
Questions about Dagster MCP Server
- How do I connect Dagster MCP Server to Claude?
- Run `claude mcp add dagster-mcp -- uvx dagster-mcp` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
- Is Dagster MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Dagster MCP Server do?
- Dagster MCP Server documents 27 tools to the agent, including backfill_assets, get_asset_details, get_asset_health. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.