How do I deploy the server?
Use the "Deploy to Workers" button or the `npm create cloudflare` command shown in the README.
@joegulags
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。
A deployment template and guide for running a remote MCP server on Cloudflare Workers with no authentication required. It is intended for developers who want to quickly expose MCP tools over SSE without building auth logic.
Click the "Deploy to Workers" button in the README to deploy instantly, or run npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless locally. After deployment, connect MCP clients (e.g., Cloudflare AI Playground or Claude Desktop) using the server’s SSE URL.
this.server.tool(...) in src/index.tsmcp-remote proxyUse the "Deploy to Workers" button or the `npm create cloudflare` command shown in the README.
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’s SSE URL, and start using the tools.
Install the `mcp-remote` proxy (`npx mcp-remote`) and add a configuration entry to Claude Desktop pointing to the server’s SSE URL.
No, this example is designed without authentication. Use it only in scenarios where auth is not needed.

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.

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

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

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
评论