Dagster MCP
未认领MCP server that wraps the Dagster GraphQL API — monitor and operate runs, assets, schedules, sensors, and backfills from any MCP client
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'dagster-mcp' -- 'uvx' 'dagster-mcp'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
27 个工具中显示 27 个
文档中列出的工具 (27)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
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