Building a Remote MCP Server on Cloudflare (Without Auth)
LocalAbout Building a Remote MCP Server on Cloudflare (Without Auth)
This example deploys an unauthenticated remote MCP server on Cloudflare Workers for analyzing websites and answering questions about their content. It uses Browser Rendering to extract pages and Cloudflare AI to summarize or answer questions.
Key features
- 01Deploy a remote MCP server on Cloudflare Workers
- 02Scrape pages with Browser Rendering
- 03Summarize website content with Cloudflare AI
- 04Answer questions about website content
Use cases
- 01Summarize a website through an MCP client
- 02Ask focused questions about a site's services
- 03Deploy a remote website-analysis server
MCP support
The server exposes `analyze_website` and `ask_q_about_website` tools to MCP clients. It can be deployed remotely on Cloudflare Workers without authentication.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEBuilding a Remote MCP Server on Cloudflare (Without Auth)
This example allows you to deploy a remote MCP server that doesn't require authentication on Cloudflare Workers. The server includes tools for website analysis and content extraction using Cloudflare's Browser Rendering and AI capabilities.
Get started:
This will deploy your MCP server to a URL like: remote-mcp-server-authless.<your-account>.workers.dev/sse
Alternatively, you can use the command line below to get the remote MCP Server created on your local machine:
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
Available Tools
Website Analysis Tools
-
analyze_website
- Scrapes and analyzes a website using Cloudflare's browser rendering
- Uses Cloudflare AI to provide a summary of the website's content
- Input:
url(string) - The website URL to analyze - Example:
[tool] analyze_website(url: "https://example.com")
-
ask_q_about_website
- Scrapes a website and answers specific questions about its content
- Uses Cloudflare AI to understand and respond to questions about the website
- Inputs:
url(string) - The website URL to analyzequestion(string) - Your question about the website content
- Example:
[tool] ask_q_about_website(url: "https://example.com", question: "What services does this company offer?")
Customizing your MCP Server
To add your own tools to the MCP server, define each tool inside the init() method of src/index.ts using this.server.tool(...).
Connect to Cloudflare AI Playground
You can connect to your MCP server from the Cloudflare AI Playground, which is a remote MCP client:
- Go to https://playground.ai.cloudflare.com/
- Enter your deployed MCP server URL (
remote-mcp-server-authless.<your-account>.workers.dev/sse) - You can now use your MCP tools directly from the playground!
Connect Claude Desktop to your MCP server
You can also connect to your remote MCP server from local MCP clients, by using the mcp-remote proxy.
To connect to your MCP server from Claude Desktop, follow Anthropic's Quickstart and within Claude Desktop go to Settings > Developer > Edit Config.
Update with this configuration:
{
"mcpServers": {
"calculator": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse" // or remote-mcp-server-authless.your-account.workers.dev/sse
]
}
}
}
Restart Claude and you should see the tools become available.
Requirements
To use the website analysis tools, you need:
- Cloudflare Workers with browser binding enabled
- Cloudflare AI binding configured
- Appropriate permissions for both bindings
Make sure your wrangler.jsonc includes:
{
"browser": {
"binding": "BROWSER"
},
"ai": {
"binding": "AI"
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.