広告掲載
MCP.so
ログイン

Building a Remote MCP Server on Cloudflare (Without Auth)

@amahara-dev

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

amahara-dev

Building a Remote MCP Server on Cloudflare について

概要はまだありません

#remote-mcp#cloudflare#server

Building a Remote MCP Server on Cloudflare の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "calculator": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8787/sse"
      ]
    }
  }
}

Building a Remote MCP Server on Cloudflare のツール

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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Building a Remote MCP Server on Cloudflare (Without Auth)?

This is a demo/template that lets you deploy a remote MCP server on Cloudflare Workers without requiring authentication. It provides a starting point for developers who want to expose MCP tools over SSE without managing user auth.

How to use Building a Remote MCP Server on Cloudflare (Without Auth)?

Deploy using the "Deploy to Workers" button (gets a public URL like remote-mcp-server-authless.<your-account>.workers.dev/sse) or run npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless locally. Customize tools by editing src/index.ts and adding tool definitions inside the init() method with this.server.tool(...). Connect from Cloudflare AI Playground by entering your SSE URL, or from Claude Desktop using the mcp-remote proxy tool and the provided JSON configuration.

Key features of Building a Remote MCP Server on Cloudflare (Without Auth)

  • Deploys a remote MCP server to Cloudflare Workers
  • Requires no authentication for MCP connections
  • Customizable tools defined in TypeScript code
  • Connects to Cloudflare AI Playground as a remote MCP client
  • Connects to Claude Desktop via the mcp-remote proxy
  • Uses SSE (Server-Sent Events) transport

Use cases of Building a Remote MCP Server on Cloudflare (Without Auth)

  • Quickly prototyping MCP-based tools without setting up authentication
  • Experimenting with remote MCP servers on Cloudflare’s edge network
  • Integrating custom tools with Cloudflare AI Playground for testing
  • Exposing MCP tools to Claude Desktop or other MCP clients via a proxy

よくある質問

1

Does the server require authentication?

No, this MCP server is intentionally built without authentication.

2

How do I deploy the server?

Click the "Deploy to Workers" button or use the `npm create cloudflare` command with the provided template.

3

How do I add my own tools?

Define each tool inside the `init()` method of `src/index.ts` by calling `this.server.tool(...)`.

4

How do I connect from Cloudflare AI Playground?

Go to the AI Playground, enter your deployed MCP server’s SSE URL, and start using the tools directly.

5

How do I connect from Claude Desktop?

Install the `mcp-remote` npm package, then add a configuration entry with `command: "npx"`, args including the remote SSE URL, and restart Claude Desktop.

コメント

「開発者ツール」の他のコンテンツ

GripForge

gripforgeai

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

1

SSH MCP Server

hypnosis

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

1

LocalCan

LocalCan

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.

82

MCP Server By TestMu AI

TestMu AI

TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche

FARPY

mangomunchr

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

1
広告掲載