Cloudflare Workers MCP
Enables deployment of MCP servers on Cloudflare Workers without authentication, allowing users to create custom tools and connect them to AI clients like Claude Desktop or Cloudflare AI Playground. Provides a template for building remote MCP servers
What is Cloudflare Workers MCP?
Cloudflare Workers MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables deployment of mcp servers on cloudflare workers without authentication, allowing users to create custom tools and connect them to ai clients like claude desktop or cloudflare ai playground. pr...
Enables deployment of MCP servers on Cloudflare Workers without authentication, allowing users to create custom tools and connect them to AI clients like Claude Desktop or Cloudflare AI Playground. Provides a template for building remote MCP servers
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables deployment of MCP servers on Cloudflare Workers with
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx remote-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cloudflare Workers MCP
Remote-MCP is a TypeScript library that lets you deploy MCP servers on any remote host — including Cloudflare Workers — and connect to them from MCP clients like Claude Desktop using a thin npx-based client proxy. It splits the architecture into a server package (@remote-mcp/server) that you deploy remotely and a client package (@remote-mcp/client) that bridges your local AI client to that remote endpoint over HTTP, optionally with Bearer token authentication. This makes it practical to share a single MCP server among multiple team members or to run compute-intensive tools in the cloud rather than on the developer's laptop.
Prerequisites
- Node.js 18+ installed locally (for running the npx client proxy)
- A deployed Remote-MCP server instance (e.g., on Cloudflare Workers) exposing an HTTP endpoint
- The remote server URL and any Bearer token for authentication
- An MCP client such as Claude Desktop or Cloudflare AI Playground
- npm or npx available in your PATH
Install the client package
Add the Remote-MCP client to your project, or use it directly with npx without installing. The client acts as a local stdio-to-HTTP bridge between your MCP host and the remote server.
npm install @remote-mcp/client @trpc/client@next zodDeploy or locate your remote MCP server
Install the server package and implement your tools using the MCPRouter API. Deploy the resulting HTTP service to Cloudflare Workers, a VPS, or any reachable host. Note the public URL of the deployed service.
npm install @remote-mcp/serverDefine tools on the server
On the server side, create an MCPRouter and register tools with input schemas. The framework serialises everything over HTTP so clients see standard MCP tool calls.
import { MCPRouter } from '@remote-mcp/server';
const router = new MCPRouter({ name: 'my-server', version: '1.0.0', capabilities: { logging: {} } });
router.addTool('add', { description: 'Add two numbers', inputSchema: { ... } }, async (input) => ({ result: input.a + input.b }));Configure Claude Desktop to use the remote server
Edit claude_desktop_config.json to add the Remote-MCP client as an MCP server entry. Set REMOTE_MCP_URL to your deployed endpoint and, if required, supply a Bearer token via HTTP_HEADER_Authorization.
{
"mcpServers": {
"remote-mcp": {
"command": "npx",
"args": ["-y", "@remote-mcp/client"],
"env": {
"REMOTE_MCP_URL": "https://your-worker.your-subdomain.workers.dev",
"HTTP_HEADER_Authorization": "Bearer YOUR_TOKEN"
}
}
}
}Restart Claude Desktop and verify
Restart Claude Desktop so it picks up the new MCP server configuration. Open a conversation and ask Claude to list available tools — you should see the tools registered on your remote server.
Cloudflare Workers MCP Examples
Client configuration
Minimal claude_desktop_config.json entry connecting Claude Desktop to a remote MCP server via the @remote-mcp/client proxy.
{
"mcpServers": {
"remote-mcp": {
"command": "npx",
"args": ["-y", "@remote-mcp/client"],
"env": {
"REMOTE_MCP_URL": "https://your-worker.your-subdomain.workers.dev",
"HTTP_HEADER_Authorization": "Bearer YOUR_TOKEN"
}
}
}
}Prompts to try
Example prompts once the remote server is connected and your tools are registered.
- "What tools are available on the remote MCP server?"
- "Add 42 and 58 using the calculator tool."
- "Run the divide operation with a=100 and b=4."
- "List all capabilities exposed by this server."Troubleshooting Cloudflare Workers MCP
Claude Desktop shows the MCP server as disconnected or unavailable
Verify REMOTE_MCP_URL is correct and reachable from your machine with curl. Check that the deployed server is running and not returning 4xx/5xx errors. Ensure the Bearer token matches what the server expects.
npx @remote-mcp/client fails with authentication errors
Confirm HTTP_HEADER_Authorization is set exactly as 'Bearer <token>' with no extra spaces. If your server does not require auth, remove that env variable entirely from the config.
Tools registered on the server do not appear in Claude
Restart Claude Desktop after saving the config. Confirm the server's MCPRouter exports tools correctly and that the server process is still alive. Check server logs for startup errors.
Frequently Asked Questions about Cloudflare Workers MCP
What is Cloudflare Workers MCP?
Cloudflare Workers MCP is a Model Context Protocol (MCP) server that enables deployment of mcp servers on cloudflare workers without authentication, allowing users to create custom tools and connect them to ai clients like claude desktop or cloudflare ai playground. provides a template for building remote mcp servers It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cloudflare Workers MCP?
Follow the installation instructions on the Cloudflare Workers MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Cloudflare Workers MCP?
Cloudflare Workers MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cloudflare Workers MCP free to use?
Yes, Cloudflare Workers MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Cloudflare Workers MCP Alternatives — Similar Developer Tools Servers
Looking for alternatives to Cloudflare Workers MCP? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cloudflare Workers MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cloudflare Workers MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.