Remote MCP Server (Authless) logo

Remote MCP Server (Authless)

by jacobprall

This example demonstrates how to deploy a remote MCP server on Cloudflare Workers without authentication. It allows you to connect to the server from the Cloudflare AI Playground or local MCP clients like Claude Desktop.

View on GitHub

Last updated: N/A

What is Remote MCP Server (Authless)?

This is a remote Model Context Protocol (MCP) server that can be deployed on Cloudflare Workers. It allows you to expose tools to MCP clients like the Cloudflare AI Playground or Claude Desktop without requiring authentication.

How to use Remote MCP Server (Authless)?

You can deploy the server using the 'Deploy to Workers' button or via the command line. After deployment, you can connect to it from the Cloudflare AI Playground by entering the server URL. For local clients like Claude Desktop, you can use the 'mcp-remote' proxy and configure the client to point to the proxy.

Key features of Remote MCP Server (Authless)

  • Serverless deployment on Cloudflare Workers

  • No authentication required

  • Easy integration with Cloudflare AI Playground

  • Support for local MCP clients via mcp-remote proxy

  • Customizable with your own tools

Use cases of Remote MCP Server (Authless)

  • Exposing custom tools to AI models

  • Connecting local applications to remote AI services

  • Building AI-powered workflows

  • Experimenting with different AI models and tools

FAQ from Remote MCP Server (Authless)

What is MCP?

MCP stands for Model Context Protocol. It's a protocol for connecting AI models with external tools and data sources.

What is Cloudflare Workers?

Cloudflare Workers is a serverless platform that allows you to run code on Cloudflare's global network.

How do I add my own tools to the MCP server?

You can define your tools inside the init() method of src/index.ts using this.server.tool(...).

What is mcp-remote?

mcp-remote is a proxy that allows you to connect local MCP clients to remote MCP servers.

Why would I want to use a remote MCP server?

Using a remote MCP server allows you to expose tools to AI models without having to run them locally. It also allows you to connect local applications to remote AI services.