Remote MCP Server on Cloudflare
@lellocb
About Remote MCP Server on Cloudflare
No overview available yet
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"remote-mcp-server-lellocb": {
"command": "npx",
"args": [
"nx",
"dev",
"remote-mcp-server"
]
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is Remote MCP Server on Cloudflare?
An MCP (Model Context Protocol) server that runs on Cloudflare Workers, complete with OAuth login. It is intended for developers who want to host and connect remote MCP tools to clients like Claude Desktop.
How to use Remote MCP Server on Cloudflare?
Clone the repository, install dependencies with npm install, then run locally with npx nx dev remote-mcp-server. Deploy to Cloudflare using npm run deploy after creating a KV namespace. Connect clients (e.g., MCP Inspector or Claude Desktop) via SSE using the worker's URL (e.g., https://worker-name.account-name.workers.dev/sse).
Key features of Remote MCP Server on Cloudflare
- Runs on Cloudflare Workers
- OAuth login support
- Uses SSE transport
- Deployable with a single command
- Local development with live reload
- Works with MCP Inspector and Claude Desktop
Use cases of Remote MCP Server on Cloudflare
- Hosting a math tool accessible via Claude Desktop
- Running a remote MCP server for custom tools
- Prototyping and testing MCP tools locally before deploying
FAQ from Remote MCP Server on Cloudflare
How do I test the server locally?
Run npx nx dev remote-mcp-server and open http://localhost:8787/. Use the MCP Inspector with SSE and URL http://localhost:8787/sse.
How do I connect Claude Desktop to the server?
Edit Claude Desktop’s config file and add an entry using npx mcp-remote with the server’s SSE URL (local http://localhost:8787/sse or remote https://worker-name.account-name.workers.dev/sse).
What dependencies are required?
Node.js and npm are needed for local development. Deployment requires a Cloudflare account and wrangler CLI.
Where is authentication data stored?
OAuth data is stored in a Cloudflare KV namespace (OAUTH_KV) created via npx wrangler kv namespace create.
How can I debug connection issues?
Restart Claude, or test the server directly with npx mcp-remote http://localhost:8787/sse. In rare cases, clear ~/.mcp-auth with rm -rf ~/.mcp-auth.
Frequently asked questions
How do I test the server locally?
Run `npx nx dev remote-mcp-server` and open `http://localhost:8787/`. Use the MCP Inspector with SSE and URL `http://localhost:8787/sse`.
How do I connect Claude Desktop to the server?
Edit Claude Desktop’s config file and add an entry using `npx mcp-remote` with the server’s SSE URL (local `http://localhost:8787/sse` or remote `https://worker-name.account-name.workers.dev/sse`).
What dependencies are required?
Node.js and npm are needed for local development. Deployment requires a Cloudflare account and `wrangler` CLI.
Where is authentication data stored?
OAuth data is stored in a Cloudflare KV namespace (`OAUTH_KV`) created via `npx wrangler kv namespace create`.
How can I debug connection issues?
Restart Claude, or test the server directly with `npx mcp-remote http://localhost:8787/sse`. In rare cases, clear `~/.mcp-auth` with `rm -rf ~/.mcp-auth`.
Basic information
More Cloud & Infrastructure MCP servers
Lambda MCP Server Demo (Streamable HTTP)
mikegc-awsCreates a simple MCP tool server with "streaming" HTTP.
container-use
aluzzardiDevelopment environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
tfmcp: Terraform Model Context Protocol Tool
nwiizo🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI assistants to manage and operate Terraform environments. Supports reading Terraform configurations, analyzing plans, applying configurations, and managing state with Claude Desktop integrati
Query | MCP server for Supabase
alexander-zuevQuery MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning, access to logs and much more.
container-use
daggerDevelopment environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
Comments