How do I deploy the server?
Use the "Deploy to Workers" button or run `npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless`.
@shlomobamberger
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"calculator": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
This template lets you deploy a remote MCP (Model Context Protocol) server on Cloudflare Workers that does not require authentication. It is aimed at developers who want to quickly set up a server with custom tools accessible from remote MCP clients like the Cloudflare AI Playground or local applications via a proxy.
Deploy by clicking the "Deploy to Workers" button or by running npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless in your terminal. Customize tools inside the init() method of src/index.ts using this.server.tool(...). Connect to the Cloudflare AI Playground by entering the deployed SSE URL, or connect Claude Desktop by configuring a mcp-remote proxy in claude_desktop_config.json.
this.server.tool() method.Use 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` by calling `this.server.tool(...)`.
Go to [playground.ai.cloudflare.com](https://playground.ai.cloudflare.com/), enter your deployed MCP server URL (ending in `/sse`), and the tools become available.
Install the `mcp-remote` npm package and configure Claude Desktop’s `claude_desktop_config.json` to use `npx mcp-remote <your-sse-url>`.
No, this example is explicitly designed without authentication to simplify deployment and testing.

Turn a plain-language guide into a narrated walkthrough video of your deployed web app. Your coding agent can write the guide from the source and bring back the MP4.

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

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

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
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.
评论