dagster-mono-mcp
dagster-mono-mcp
一个用于 Dagster 的单工具 MCP 服务器。一个工具,五个操作,极低的 Token 开销。
Dagster 有一个 官方 MCP 服务器,但我无法轻松使其运行。这是一个极简的替代方案,涵盖了您在使用 LLM 调试流水线时真正需要的操作:列出运行、检查运行详情、读取日志以及用于其他所有操作的原始 GraphQL。
支持 Cloudflare Access,适用于位于 Zero Trust 之后的 Dagster 实例——这是一种保护 Dagster 实例的简单且免费的方法。
安装
Claude Code
项目范围(在项目根目录下的 .mcp.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"
}
}
}
}全局(~/.claude.json — 在所有项目中可用):
{
"mcpServers": {
"dagster": {
"command": "npx",
"args": ["-y", "github:pjatx/dagster-mono-mcp"],
"env": {
"DAGSTER_GRAPHQL_URL": "https://dagster.example.com/graphql"
}
}
}
}Cursor
添加到项目根目录下的 .cursor/mcp.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"
}
}
}
}Windsurf
添加到 ~/.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
环境变量
变量 | 默认值 | 必需 |
|
| 否 |
| — | 否(如果位于 CF Access 之后则必需) |
| — | 否(如果位于 CF Access 之后则必需) |
使用方法
带有操作分发的单一工具 dagster:
列出运行
{"action": "runs"}
{"action": "runs", "status": "FAILURE"}
{"action": "runs", "job": "my_job", "limit": 5}运行详情
{"action": "run", "id": "<run-id>"}事件日志
{"action": "logs", "id": "<run-id>"}
{"action": "logs", "id": "<run-id>", "limit": 100}原始 GraphQL
{"action": "graphql", "query": "{ version }"}
{"action": "graphql", "query": "query($id: ID!) { runOrError(runId: $id) { __typename } }", "variables": {"id": "abc123"}}帮助
{"action": "help"}返回完整文档,包括可用状态、所有参数和示例查询。
设计
本项目遵循单工具模式:一个带有操作分发的 MCP 工具,而不是许多小工具。更少的工具意味着 LLM 的 Token 开销更低,工具选择也更简单——模型不必在十几个听起来相似的工具之间进行选择。灵感来自 Cloudflare 关于重新思考 LLM 如何与 MCP 服务器交互的 Code Mode 文章。
开发
npm install
npm run build # esbuild bundle -> dist/index.js
npm start # run the MCP server (stdio transport)许可证
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.-