cloudflare

Workers MCP — DevOps skill for Claude Code

DevOps community

Talk to a Cloudflare Worker from Claude Desktop.

How to install Workers MCP

This entry records only its repository, not the path inside it, so there is no exact command to give. Open cloudflare/workers-mcp and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Workers MCP does

Talk to a Cloudflare Worker from Claude Desktop!

Alternatives in DevOps

  • Cloudflare Deploy — Deploy apps to Cloudflare using Workers, Pages, and platform services 14.6k ★
  • Kubeshark — Cluster-wide network observability for Kubernetes 11.8k ★
  • MCP Boilerplate — A remote Cloudflare MCP server boilerplate with user authentication and Stripe for paid tools 1k ★

README

`workers-mcp`

**Talk to a Cloudflare Worker from Claude Desktop!**

[!WARNING] You should start [here](https://developers.cloudflare.com/agents/guides/remote-mcp-server/) instead — and build a **remote** MCP server

You can connect to remote MCP servers from Claude Desktop, Cursor, and other clients [using mcp-remote](https://developers.cloudflare.com/agents/guides/test-remote-mcp-server/).

What is `workers-mcp`?

This package provides both the CLI tooling and the in-Worker logic to connect Claude Desktop (or any [MCP Client](https://modelcontextprotocol.io/)) to a Cloudflare Worker on your account, so you can customise it to suit your needs. It works via a build step that can translate TypeScript methods of your Worker like this:

export class ExampleWorkerMCP extends WorkerEntrypoint {
  /**
   * Generates a random number. This is extra random because it had to travel all the way to
   * your nearest Cloudflare PoP to be calculated which... something something lava lamps?
   *
   * @return {string} A message containing a super duper random number
   * */
  async getRandomNumber() {
    return `Your random number is ${Math.random()}`
  }
  
  // ...etc
}

...into MCP tools that a local Node.js server can expose to MCP clients. The Node.js server acts as a proxy, handling stdio transport locally, and calling the relevant method of your Worker running on Cloudflare. This allows you to expose any function or API in your app, or any service in [Cloudflare's developer platform](https://developers.cloudflare.com/products/), back to a LLM in your coding agent, Claude Desktop or other MCP client.

![image](https://github.com/user-attachments/assets/c16b2631-4eba-4914-8e26-d6ccea0fc578)

Yes, I know that `Math.random()` works the same on a Worker as it does on your local machine, but don't tell Claude 🤫

Usage

Step 1: Generate a new Worker

Use `create-cloudflare` to generate a new Worker.

npx create-cloudfla