@dyeoman2
基本情報
A production-ready template for building Model Context Protocol (MCP) servers with Clerk authentication on Cloudflare Workers
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A production-ready template for building Model Context Protocol (MCP) servers that integrate Clerk authentication with Cloudflare Workers. It provides a complete OAuth 2.0 flow, Durable Objects for session state, and KV storage for temporary OAuth sessions. Designed for developers who want to connect their existing Clerk-authenticated applications to Claude AI through secure MCP tools.
Clone the repository, run npm install, configure environment variables (CLERK_SECRET_KEY, CLERK_PUBLISHABLE_KEY, APP_URL) in a .dev.vars file, create a KV namespace with Wrangler, update the namespace ID in wrangler.jsonc, and start the development server with npm run dev. Requires Node.js 22+, a Clerk account, a Cloudflare account with Workers enabled, and an existing application using Clerk for authentication.
It bridges your existing Clerk-authenticated application with Claude AI through MCP tools. Unlike generic MCP servers, it provides a ready-made OAuth flow and session management tailored for Clerk, reducing integration effort.
You need Node.js 22+, a Clerk account with API keys, a Cloudflare account with Workers enabled, and an existing application that uses Clerk for authentication.
OAuth session data is stored temporarily in Cloudflare KV. MCP session state is managed in Durable Objects. All application data remains in your existing Clerk-powered application.
The server uses SSE (Server-Sent Events) transport and OAuth 2.0 authentication with Clerk. JWT tokens are used for API requests, and state parameters are protected with HMAC signatures.
The README does not list hard limits, but the template relies on Cloudflare Workers and Durable Objects – scale and performance depend on those platforms. OAuth sessions in KV expire automatically.
Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
Open-source Next.js + Supabase CMS with a per-site MCP server: scaffold a site, then create pages, posts, navigation, media and SEO from Claude, Cursor or any MCP client. Streamable HTTP with a bearer token you mint in y
MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
コメント