How do I deploy this MCP server?
Click the "Deploy to Workers" button or run `npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless` from the command line.
@hachecito
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",
"remote-mcp-server-authless.your-account.workers.dev/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 template and deployment method for creating a remote MCP (Model Context Protocol) server on Cloudflare Workers that does not require authentication. It is intended for developers who want to quickly stand up a serverless MCP endpoint with custom tools and access it from remote MCP clients.
Deploy using the "Deploy to Workers" button or run npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless. Customize tools inside the init() method of src/index.ts using this.server.tool(...). Connect from Cloudflare AI Playground by entering the deployed SSE URL, or from Claude Desktop via the mcp-remote proxy.
Click the "Deploy to Workers" button or run `npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless` from the command line.
Define each tool inside the `init()` method of `src/index.ts` using `this.server.tool(...)`.
Go to the playground URL, enter your deployed MCP server’s SSE URL (e.g., `remote-mcp-server-authless.<your-account>.workers.dev/sse`), and use your tools directly.
Use the `mcp-remote` npm proxy. In Claude Desktop settings, add a server entry with `command: "npx"`, args including `mcp-remote` and your SSE URL.
The server runs on Cloudflare Workers. Local development requires Node.js and the `npm create cloudflare` CLI. The mcp-remote proxy (for local clients) is an additional npm package.

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.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
Get a second opinion on your code from every coding agent you have. Claude Code, Codex and Grok review each other's diffs and answer each other's questions, even inside a session that's already running. Uses the CLIs you

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
评论