How does this differ from an authenticated MCP server?
This server intentionally omits authentication, making setup simpler but less secure. It is intended for development/testing or internal use where auth is not required.
@rita3ko
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 example demonstrates how to deploy a remote MCP server that requires no authentication on Cloudflare Workers. It is intended for developers who want to quickly stand up an MCP server and connect it to remote MCP clients like the Cloudflare AI Playground or Claude Desktop.
Deploy by clicking the "Deploy to Workers" button or running npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless. This creates a server at a URL like remote-mcp-server-authless.<account>.workers.dev/sse. Customize by adding tools inside the init() method of src/index.ts using this.server.tool(...).
This server intentionally omits authentication, making setup simpler but less secure. It is intended for development/testing or internal use where auth is not required.
The server runs on Cloudflare Workers. Deployment requires a Cloudflare account and optionally Node.js/npm for local creation via the CLI.
The server itself is stateless; any tool state or data is handled inside the Cloudflare Worker’s runtime and is not persisted beyond a request unless explicitly stored by a tool.
The server communicates over Server-Sent Events (SSE) at the `/sse` endpoint.
The README covers only the no-auth version. Adding authentication would require modifying the worker and is outside the scope of this example.

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.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

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

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
评论