How do I deploy this MCP server?
Click the "Deploy to Workers" button in the README, or run the `npm create cloudflare` command with the provided template.
@tomkingchen
基本信息
暂无概览
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。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
This server enables deployment of a remote MCP (Model Context Protocol) server that requires no authentication on Cloudflare Workers. It is intended for developers who want to expose MCP tools publicly without a login barrier.
Deploy by clicking the "Deploy to Workers" button or run npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless locally. Customize tools by editing src/index.ts inside the init() method using this.server.tool(...). Connect to the Cloudflare AI Playground (https://playground.ai.cloudflare.com/) by entering the deployed SSE URL, or connect Claude Desktop via the mcp-remote proxy with the JSON configuration shown in the README.
/sse) for remote MCP clients.src/index.ts.mcp-remote proxy.Click the "Deploy to Workers" button in the README, or run the `npm create cloudflare` command with the provided template.
You need Node.js and npm to create the project locally; the deployed Worker runs on Cloudflare’s runtime. For local clients, the `mcp-remote` npm package is needed.
All MCP server logic runs on Cloudflare Workers, and data is managed within the Worker’s environment. No persistent storage is configured by default.
It listens for SSE connections at the deployed Workers URL (e.g., `remote-mcp-server-authless.<your-account>.workers.dev/sse`). No authentication is enforced.
Yes, by running the `mcp-remote` proxy locally and pointing your client to the proxy’s address, as shown in the README’s JSON configuration example.

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
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.

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a

Leadpages MCP is a remote MCP server available at https://mcp.leadpages.com.

Real UI references for AI coding agents: 500,000+ real screens, 15k+ website design systems with a DESIGN.md, and 30k+ UI elements, so your agent builds UI that looks real, not AI slop.
评论