How do I deploy the MCP server?
Use the “Deploy to Workers” button or run `npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless`.
@StevenConnors
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 allows you to deploy a remote MCP server that doesn’t require authentication on Cloudflare Workers. It is intended for developers who want to host MCP tools on a remote server accessible via SSE, without a full authentication system.
Deploy via the “Deploy to Workers” button or run npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless. Add custom tools in src/index.ts using this.server.tool(...). Connect clients such as Cloudflare AI Playground or Claude Desktop (via the mcp-remote proxy) to the deployed SSE URL.
src/index.tsUse the “Deploy to Workers” button or run `npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless`.
Define each tool inside the `init()` method of `src/index.ts` using `this.server.tool(...)`.
Go to https://playground.ai.cloudflare.com/, enter your deployed MCP server URL (e.g., `remote-mcp-server-authless.<your-account>.workers.dev/sse`).
Use the mcp-remote proxy and configure Claude Desktop’s `mcpServers` setting with the command `npx mcp-remote <server-url>`.
The server exposes an SSE endpoint at `/sse`.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links

コメント