Remote MCP Server logo

Remote MCP Server

by MCP-Mirror

This project provides a remote MCP (Model Context Protocol) server that can be deployed on Cloudflare Workers. It allows you to connect MCP clients like the MCP Inspector and Claude Desktop to a remote server for tool execution.

View on GitHub

Last updated: N/A

What is Remote MCP Server?

This is a remote MCP server implementation designed to run on Cloudflare Workers. It enables you to expose tools and functionalities defined using the Model Context Protocol (MCP) to remote clients like the MCP Inspector and Claude Desktop.

How to use Remote MCP Server?

  1. Develop locally using the provided instructions (clone, install dependencies, run locally). 2. Deploy to Cloudflare using Wrangler. 3. Connect MCP Inspector or Claude Desktop by configuring them to point to the deployed server's URL (workers.dev).

Key features of Remote MCP Server

  • Remote MCP server deployment

  • Cloudflare Workers integration

  • OAuth login support

  • SSE (Server-Sent Events) transport

  • Integration with MCP Inspector and Claude Desktop

Use cases of Remote MCP Server

  • Exposing custom tools to AI models like Claude

  • Building serverless AI applications

  • Creating a centralized MCP server for multiple clients

  • Testing and debugging MCP tools remotely

FAQ from Remote MCP Server

How do I connect the MCP Inspector?

Start the inspector, switch the Transport Type to SSE, and enter the server's URL (e.g., http://localhost:8787/sse or worker-name.account-name.workers.dev/sse).

How do I connect Claude Desktop?

Edit the Claude configuration file (Settings > Developer > Edit Config) and update the mcpServers section to point to the server's URL.

What if something goes wrong?

Try restarting Claude or connecting directly to the MCP server using npx mcp-remote <server_url>.

How do I clear auth files?

Remove the files in ~/.mcp-auth using rm -rf ~/.mcp-auth.

How do I deploy to Cloudflare?

  1. Create a KV namespace: npx wrangler kv namespace create OAUTH_KV. 2. Add the KV namespace ID to wrangler.jsonc. 3. Run npm run deploy.