What does this example do?
It provides a template to deploy a remote MCP server on Cloudflare Workers that does not require authentication, making it easy to expose MCP tools over SSE.
@jacobprall
基本情報
概要はまだありません
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。
This example provides a template to deploy a remote MCP server on Cloudflare Workers that does not require authentication. It is intended for developers who want to quickly set up a remote MCP server with custom tools and connect it to clients like Cloudflare AI Playground or Claude Desktop.
Deploy the server by clicking the "Deploy to Workers" button or running npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless from the command line. Customize tools by defining them in the init() method of src/index.ts using this.server.tool(...). Connect to Cloudflare AI Playground by entering the deployed URL, or to Claude Desktop using the mcp-remote proxy with the server's SSE endpoint.
src/index.ts.mcp-remote proxy.It provides a template to deploy a remote MCP server on Cloudflare Workers that does not require authentication, making it easy to expose MCP tools over SSE.
Click the "Deploy to Workers" button in the README or run `npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless` to create it locally.
Define each tool inside the `init()` method of `src/index.ts` using `this.server.tool(...)` as shown in the Cloudflare MCP tools documentation.
Go to https://playground.ai.cloudflare.com/, enter your deployed MCP server URL (e.g., `remote-mcp-server-authless.<your-account>.workers.dev/sse`), and you can use the tools directly.
Install the `mcp-remote` proxy, then add the server to Claude Desktop's configuration using `npx mcp-remote <sse-url>` as the command and args.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott


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

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
コメント