Remote MCP Server
by admin-amaravati-io
This project provides a remote MCP (Model Context Protocol) server that can be deployed on Cloudflare Workers, complete with OAuth login. It allows you to connect to the server using the MCP Inspector or Claude Desktop.
Last updated: N/A
What is Remote MCP Server?
This is a remote MCP server implementation designed to run on Cloudflare Workers. It facilitates communication between AI models (like Claude) and external tools using the Model Context Protocol.
How to use Remote MCP Server?
To use this server, you first need to deploy it to Cloudflare Workers following the provided instructions. Then, you can connect to it using the MCP Inspector or configure Claude Desktop to utilize the server for tool invocation.
Key features of Remote MCP Server
Remote MCP server
Cloudflare Workers deployment
OAuth login
MCP Inspector compatibility
Claude Desktop integration
Use cases of Remote MCP Server
Connecting AI models to external tools
Enabling AI models to perform tasks using external APIs
Providing a secure and scalable MCP server
Integrating AI models with custom tools and services
FAQ from Remote MCP Server
How do I connect to the server locally?
How do I connect to the server locally?
Use the MCP Inspector and set the Transport Type to SSE, then enter http://localhost:8787/sse
as the URL.
How do I deploy the server to Cloudflare?
How do I deploy the server to Cloudflare?
Create a KV namespace, add the namespace ID to wrangler.jsonc
, and run npm run deploy
.
How do I connect Claude Desktop to the server?
How do I connect Claude Desktop to the server?
Update the Claude configuration file to point to the server's URL (either local or deployed) and restart Claude.
What if something goes wrong?
What if something goes wrong?
Try restarting Claude or connecting directly to the MCP server on the command line using npx mcp-remote http://localhost:8787/sse
. Clearing the files in ~/.mcp-auth
may also help.
What is MCP?
What is MCP?
MCP stands for Model Context Protocol. It's a protocol that allows AI models to interact with external tools and services.