Skip to main content
Glama
deenesjakoruzh
pjatx

dagster-mono-mcp

by pjatx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

dagster-mono-mcp

A single-tool MCP server for Dagster. One tool, five actions, minimal token overhead.

Dagster has an official MCP server, but I couldn't get it working easily. This is a minimal alternative that covers the actions you actually need when debugging pipelines with an LLM: listing runs, inspecting run details, reading logs, and raw GraphQL for everything else.

Supports Cloudflare Access for Dagster instances behind Zero Trust — an easy, free way to secure your Dagster instance.

Install

Claude Code

Project-scoped (.mcp.json in your project root):

{
  "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 — available in all projects):

{
  "mcpServers": {
    "dagster": {
      "command": "npx",
      "args": ["-y", "github:pjatx/dagster-mono-mcp"],
      "env": {
        "DAGSTER_GRAPHQL_URL": "https://dagster.example.com/graphql"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

{
  "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

Add to ~/.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

Environment Variables

Variable

Default

Required

DAGSTER_GRAPHQL_URL

http://localhost:3000/graphql

No

CF_ACCESS_CLIENT_ID

—

No (required if behind CF Access)

CF_ACCESS_CLIENT_SECRET

—

No (required if behind CF Access)

Usage

Single tool dagster with action dispatch:

List runs

{"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"}}

Help

{"action": "help"}

Returns full documentation including available statuses, all parameters, and example queries.

Design

This project follows the mono-tool pattern: one MCP tool with action dispatch instead of many small tools. Fewer tools means less token overhead for the LLM and simpler tool selection — the model doesn't have to choose between a dozen similar-sounding tools. Inspired by Cloudflare's Code Mode post on rethinking how LLMs interact with MCP servers.

Development

npm install
npm run build    # esbuild bundle -> dist/index.js
npm start        # run the MCP server (stdio transport)

License

MIT

Available Tools

1 tool
dagsterC

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

ParametersJSON Schema
NameRequiredDescriptionDefault
actionYes
idNo
jobNo
statusNo
limitNo
queryNo
variablesNo

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what each action does (e.g., 'recent runs', 'run details'), but lacks critical behavioral traits such as authentication requirements, rate limits, error handling, or whether actions are read-only or destructive. The examples imply read operations but don't explicitly state safety.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded with a brief purpose statement followed by action examples. Each sentence earns its place by illustrating usage, though it could be more structured (e.g., bullet points) and the initial line is somewhat vague.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (7 parameters, no output schema, no annotations), the description is incomplete. It covers actions and some parameters but misses details on return values, error cases, and full parameter semantics. Without annotations or output schema, more behavioral and contextual information is needed for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds significant meaning beyond the input schema, which has 0% description coverage. It explains what each action does and provides example parameter combinations (e.g., 'runs' with 'status', 'run' with 'id'), clarifying how parameters interact. However, it doesn't cover all 7 parameters (e.g., 'job', 'limit', 'variables' are unexplained), so it doesn't fully compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool is for 'Dagster runs & debugging' and lists five actions, which gives a general purpose but lacks specificity about what Dagster is or what resources it operates on. It distinguishes between actions but doesn't clearly articulate the overall tool's function beyond listing sub-actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, as there are no sibling tools mentioned. It lists actions with examples but doesn't explain prerequisites, contexts, or exclusions for usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observeddagster
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count2/5

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.

Completeness3/5

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

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Access OAuth Server

    Ena-turcotte6
    F
    license
    Not graded
    quality
    C
    maintenance
    A 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.
    -

  • remote-mcp-server

    Gagan1729-droid
    F
    license
    Not graded
    quality
    C
    maintenance
    This is an MCP server deployed on Cloudflare Workers with OAuth authentication, enabling remote MCP clients to connect and use tools.
    -