mcp-dagster
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DAGSTER_MCP_PORT | No | HTTP port used by the containerized streamable-HTTP server. | 8000 |
| DAGSTER_MCP_CONFIG | No | Path to the YAML configuration file. If unset, the server checks ./config.yaml, then ~/.config/mcp-dagster/config.yaml. | |
| DAGSTER_MCP_TIMEOUT | No | Request timeout in seconds. | 30 |
| DAGSTER_MCP_BASE_URL | No | Base URL of the Dagster instance. The GraphQL API is contacted at <base_url>/api. | |
| DAGSTER_MCP_API_TOKEN | No | Bearer token for the Dagster API. Recommended to provide via environment variable rather than the YAML file. | |
| DAGSTER_MCP_READ_ONLY | No | Read-only mode flag. Accepts 0/1 or true/false. When enabled, all GraphQL write operations are refused. | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| dagster_overviewB | Vue d'ensemble de l'instance Dagster : nom du dépôt, liste des jobs, 10 derniers runs, backfills et schedules actifs. |
| dagster_list_assetsB | Liste des assets Dagster avec leur code version, dernière matérialisation et nombre de partitions. |
| dagster_asset_stateC | État et métadonnées d'un asset (key = chemin, ex. "ch.dataset" ou "ch/dataset" ; le « . » est normalisé en « / »). |
| dagster_list_runsB | Liste des runs (optionnel : filtre par job et/ou statut, ex. SUCCESS, FAILURE, RUNNING, CANCELLED). |
| dagster_run_detailB | Détail d'un run Dagster (id du run) : statut, job, tags, métadonnées de run et état de chaque step. |
| dagster_sensors_schedulesB | Sensors et schedules de l'instance avec leur état. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct resource: instance summary, asset list, single asset state, run list, single run detail, and sensors/schedules. The only soft overlap is dagster_overview, which summarizes runs and schedules that dagster_list_runs and dagster_sensors_schedules also expose, but the descriptions make the summary-vs-detail distinction clear enough.
All tools share the dagster_ prefix and snake_case, giving a predictable namespace. Most follow a verb_noun shape (list_assets, list_runs, run_detail, asset_state), with dagster_overview and dagster_sensors_schedules being minor deviations but still readable.
Six tools is well-scoped for a Dagster observability surface, covering summary, assets, runs, and schedules without redundancy. Every tool earns its place and nothing feels like filler.
The surface is read-only: there is no way to launch or re-run a job, trigger a backfill (despite backfills being mentioned in the overview), or materialize an asset, and no run logs access. These are notable gaps for an agent trying to act on Dagster, though inspection workflows are well covered.