Workers MCP
An MCP transport for interacting with your own Cloudflare Worker.
workers-mcp
Talk to a Cloudflare Worker from Claude Desktop!
[!WARNING]
You should start here instead — and build a remote MCP serverYou can connect to remote MCP servers from Claude Desktop, Cursor, and other clients using mcp-remote.
What is workers-mcp?
This package provides both the CLI tooling and the in-Worker logic to connect Claude Desktop (or any MCP Client) 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<Env> {
/**
* 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, back to a LLM in your coding agent, Claude Desktop or other MCP client.
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-cloudflare@latest my-new-worker
I suggest choosing a Hello World worker.
Step 2: Install workers-mcp
cd my-new-worker # I always forget this bit
npm install workers-mcp
Step 3: Run the setup command
npx workers-mcp setup
Note: if something goes wrong, run npx workers-mcp help
Step 4..♾️: Iterating
After changing your Worker code, you only need to run npm run deploy to update both Claude's metadata about your function and your live Worker instance.
However, if you change the names of your methods, or their parameters, or add or remove methods, Claude will not see the updates until you restart it.
You shouldn't ever need to rerun npx workers-mcp install:claude, but it's safe to do so if you want to rule out Claude config as a source of errors.
Using with Other MCP Clients
Cursor
To get your Cloudflare MCP server working in Cursor, you need to combine the 'command' and 'args' from your config file into a single string and use type 'command'.
For example, if your config file looks like:
{
"mcpServers": {
"your-mcp-server-name": {
"command": "/path/to/workers-mcp",
"args": [
"run",
"your-mcp-server-name",
"https://your-server-url.workers.dev",
"/path/to/your/project"
],
"env": {}
}
}
}
In Cursor, create an MCP server entry with:
- type:
command - command:
/path/to/workers-mcp run your-mcp-server-name https://your-server-url.workers.dev /path/to/your/project
Other MCP Clients
For Windsurf and other MCP clients, update your configuration file to include your worker so you could use the tools directly from the client:
{
"mcpServers": {
"your-mcp-server-name": {
"command": "/path/to/workers-mcp",
"args": [
"run",
"your-mcp-server-name",
"https://your-server-url.workers.dev",
"/path/to/your/project"
],
"env": {}
}
}
}
Make sure to replace the placeholders with your actual server name, URL, and project path.
Examples
See the examples directory for a few ideas of what to use this for:
examples/01-hello-worldis a snapshot taken after the installation instructions aboveexamples/02-image-generationuses Workers AI to run the Flux image generation model. Claude is really good at suggesting prompts and can actually interpret the outcome and decide what new prompts to try to achieve the outcome you want.- TODO Browser Rendering
- TODO Durable Objects
Servidores relacionados
AWS SSO
Interact with AWS resources using Single Sign-On (SSO). Supports SSO login, listing accounts/roles, and executing AWS CLI commands.
Presso
AI-powered analytics platform connecting e-commerce and marketing data (GA4, Google Ads, Meta Ads, Shopify, Search Console) to AI assistants via MCP.
Chronicle SecOps
Interact with Google's Chronicle Security Operations suite.
Datadog MCP Server
An MCP server for the Datadog API, allowing you to search logs and traces.
Giant Swarm App Platform
A server for managing Giant Swarm App Platform deployments using Kubernetes credentials.
Gemini Image Analysis
Analyzes image and video content from URLs or local files using the Gemini 2.0 Flash model.
ONOS MCP Server
An MCP server for managing ONOS (Open Network Operating System) networks.
StreamNative MCP Server
Integrate AI agents with StreamNative Cloud resources and Apache Kafka/Pulsar messaging systems.
Replicate Designer
Generate images using Replicate's Flux 1.1 Pro model.
Gemini Cloud Assist
An MCP Server that connects to Gemini Cloud Assist APIs, enabling you to manage and troubleshoot your Google Cloud environment using natural language.