dagster-mono-mcp
dagster-mono-mcp
Un servidor MCP de herramienta única para Dagster. Una herramienta, cinco acciones, sobrecarga mínima de tokens.
Dagster tiene un servidor MCP oficial, pero no pude hacerlo funcionar fácilmente. Esta es una alternativa mínima que cubre las acciones que realmente necesitas al depurar pipelines con un LLM: listar ejecuciones, inspeccionar detalles de ejecución, leer registros y GraphQL sin procesar para todo lo demás.
Admite Cloudflare Access para instancias de Dagster detrás de Zero Trust: una forma fácil y gratuita de proteger tu instancia de Dagster.
Instalación
Claude Code
Ámbito del proyecto (.mcp.json en la raíz de tu proyecto):
{
"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 — disponible en todos los proyectos):
{
"mcpServers": {
"dagster": {
"command": "npx",
"args": ["-y", "github:pjatx/dagster-mono-mcp"],
"env": {
"DAGSTER_GRAPHQL_URL": "https://dagster.example.com/graphql"
}
}
}
}Cursor
Añadir a .cursor/mcp.json en la raíz de tu proyecto:
{
"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
Añadir a ~/.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
Variables de entorno
Variable | Predeterminado | Requerido |
|
| No |
| — | No (requerido si está detrás de CF Access) |
| — | No (requerido si está detrás de CF Access) |
Uso
Herramienta única dagster con despacho de acciones:
Listar ejecuciones
{"action": "runs"}
{"action": "runs", "status": "FAILURE"}
{"action": "runs", "job": "my_job", "limit": 5}Detalles de ejecución
{"action": "run", "id": "<run-id>"}Registros de eventos
{"action": "logs", "id": "<run-id>"}
{"action": "logs", "id": "<run-id>", "limit": 100}GraphQL sin procesar
{"action": "graphql", "query": "{ version }"}
{"action": "graphql", "query": "query($id: ID!) { runOrError(runId: $id) { __typename } }", "variables": {"id": "abc123"}}Ayuda
{"action": "help"}Devuelve la documentación completa, incluidos los estados disponibles, todos los parámetros y consultas de ejemplo.
Diseño
Este proyecto sigue el patrón de mono-herramienta: una herramienta MCP con despacho de acciones en lugar de muchas herramientas pequeñas. Menos herramientas significa menos sobrecarga de tokens para el LLM y una selección de herramientas más sencilla: el modelo no tiene que elegir entre una docena de herramientas con nombres similares. Inspirado en la publicación de Code Mode de Cloudflare sobre cómo repensar la forma en que los LLM interactúan con los servidores MCP.
Desarrollo
npm install
npm run build # esbuild bundle -> dist/index.js
npm start # run the MCP server (stdio transport)Licencia
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.-