dagster-mono-mcp
dagster-mono-mcp
Ein MCP-Server mit einem einzigen Tool für Dagster. Ein Tool, fünf Aktionen, minimaler Token-Overhead.
Dagster hat einen offiziellen MCP-Server, aber ich konnte ihn nicht einfach zum Laufen bringen. Dies ist eine minimale Alternative, die die Aktionen abdeckt, die man beim Debuggen von Pipelines mit einem LLM tatsächlich benötigt: Auflisten von Runs, Überprüfen von Run-Details, Lesen von Logs und rohes GraphQL für alles andere.
Unterstützt Cloudflare Access für Dagster-Instanzen hinter Zero Trust – eine einfache, kostenlose Möglichkeit, Ihre Dagster-Instanz abzusichern.
Installation
Claude Code
Projektbezogen (.mcp.json in Ihrem Projektstammverzeichnis):
{
"mcpServers": {
"dagster": {
"command": "npx",
"args": ["-y", "github:pjatx/dagster-mono-mcp"],
"env": {
"DAGSTER_GRAPHQL_URL": "https://dagster.example.com/graphql",
"CF_ACCESS_CLIENT_ID": "your-client-id",
"CF_ACCESS_CLIENT_SECRET": "your-client-secret"
}
}
}
}Global (~/.claude.json — verfügbar in allen Projekten):
{
"mcpServers": {
"dagster": {
"command": "npx",
"args": ["-y", "github:pjatx/dagster-mono-mcp"],
"env": {
"DAGSTER_GRAPHQL_URL": "https://dagster.example.com/graphql"
}
}
}
}Cursor
Hinzufügen zu .cursor/mcp.json in Ihrem Projektstammverzeichnis:
{
"mcpServers": {
"dagster": {
"command": "npx",
"args": ["-y", "github:pjatx/dagster-mono-mcp"],
"env": {
"DAGSTER_GRAPHQL_URL": "https://dagster.example.com/graphql",
"CF_ACCESS_CLIENT_ID": "your-client-id",
"CF_ACCESS_CLIENT_SECRET": "your-client-secret"
}
}
}
}Windsurf
Hinzufügen zu ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"dagster": {
"command": "npx",
"args": ["-y", "github:pjatx/dagster-mono-mcp"],
"env": {
"DAGSTER_GRAPHQL_URL": "https://dagster.example.com/graphql",
"CF_ACCESS_CLIENT_ID": "your-client-id",
"CF_ACCESS_CLIENT_SECRET": "your-client-secret"
}
}
}
}Related MCP server: MCP Access OAuth Server
Umgebungsvariablen
Variable | Standard | Erforderlich |
|
| Nein |
| — | Nein (erforderlich bei CF Access) |
| — | Nein (erforderlich bei CF Access) |
Verwendung
Einzelnes Tool dagster mit Aktions-Dispatch:
Runs auflisten
{"action": "runs"}
{"action": "runs", "status": "FAILURE"}
{"action": "runs", "job": "my_job", "limit": 5}Run-Details
{"action": "run", "id": "<run-id>"}Event-Logs
{"action": "logs", "id": "<run-id>"}
{"action": "logs", "id": "<run-id>", "limit": 100}Raw GraphQL
{"action": "graphql", "query": "{ version }"}
{"action": "graphql", "query": "query($id: ID!) { runOrError(runId: $id) { __typename } }", "variables": {"id": "abc123"}}Hilfe
{"action": "help"}Gibt die vollständige Dokumentation zurück, einschließlich verfügbarer Status, aller Parameter und Beispielabfragen.
Design
Dieses Projekt folgt dem Mono-Tool-Muster: ein MCP-Tool mit Aktions-Dispatch anstelle vieler kleiner Tools. Weniger Tools bedeuten weniger Token-Overhead für das LLM und eine einfachere Tool-Auswahl – das Modell muss nicht zwischen einem Dutzend ähnlich klingender Tools wählen. Inspiriert durch den Code Mode-Beitrag von Cloudflare zum Überdenken der Interaktion von LLMs mit MCP-Servern.
Entwicklung
npm install
npm run build # esbuild bundle -> dist/index.js
npm start # run the MCP server (stdio transport)Lizenz
MIT
Available Tools
1 tooldagsterC
Dagster runs & debugging. Actions: runs, run, logs, graphql, help
{"action": "runs"} -> recent runs {"action": "runs", "status": "FAILURE"} -> failed runs {"action": "run", "id": "abc123"} -> run details {"action": "logs", "id": "abc123"} -> run logs {"action": "graphql", "query": "{ version }"} -> raw GraphQL {"action": "help"} -> full documentation
Inputs: action (required), id, job, status, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
The single tool 'dagster' has clearly distinct actions (runs, run, logs, graphql, help) with no overlap in purpose. Each action targets a specific operation within the Dagster domain, making misselection impossible.
The tool naming is perfectly consistent as there is only one tool, 'dagster', and its actions follow a clear, uniform pattern (e.g., 'runs', 'run', 'logs') without any mixing of conventions or styles.
With only one tool, the server feels thin for a Dagster monitoring/debugging domain, as it bundles multiple distinct operations (e.g., querying runs, fetching logs, GraphQL) into a single tool. This may limit clarity and usability compared to a more granular tool set.
The tool covers core operations like retrieving runs, logs, and GraphQL queries, but lacks obvious lifecycle actions such as triggering new runs, pausing/resuming, or managing assets. This creates notable gaps for a full Dagster debugging workflow.
Maintenance
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Zero-dependency Cloudflare Worker gateway turning websites and REST APIs into MCP tools.
Cloudflare Workers MCP server: ai-cost-optimizer
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceA Cloudflare Workers-based MCP server that enables deployment of custom tools accessible via the Model Context Protocol without authentication requirements.-
- FlicenseNot gradedqualityCmaintenanceA Cloudflare Workers-based MCP server that enables secure remote connections using built-in OAuth authentication via Cloudflare Access. It provides identity-based access control for MCP tools and supports persistent state management through Durable Objects and SSE.-
- FlicenseNot gradedqualityDmaintenanceRemote MCP server with built-in OAuth authentication via Cloudflare Access, enabling secure tool invocation after user sign-in.-
- FlicenseNot gradedqualityNot gradedmaintenanceThis is an MCP server deployed on Cloudflare Workers with OAuth authentication, enabling remote MCP clients to connect and use tools.-