Remote MCP Server on Cloudflare
Let's get a remote MCP server up-and-running on Cloudflare Workers complete with OAuth login!
Develop locally
# clone the repository
git clone [email protected]:cloudflare/ai.git
# install dependencies
cd ai
npm install
# run locally
npx nx dev remote-mcp-server
You should be able to open http://localhost:8787/ in your browser
Connect the MCP inspector to your server
To explore your new MCP api, you can use the MCP Inspector.
- Start it with
npx @modelcontextprotocol/inspector - Within the inspector, switch the Transport Type to
SSEand enterhttp://localhost:8787/sseas the URL of the MCP server to connect to, and click "Connect" - You will navigate to a (mock) user/password login screen. Input any email and pass to login.
- You should be redirected back to the MCP Inspector and you can now list and call any defined tools!
Connect Claude Desktop to your local MCP server
The MCP inspector is great, but we really want to connect this to Claude! Follow Anthropic's Quickstart and within Claude Desktop go to Settings > Developer > Edit Config to find your configuration file.
Open the file in your text editor and replace it with this configuration:
{
"mcpServers": {
"math": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse"
]
}
}
}
This will run a local proxy and let Claude talk to your MCP server over HTTP
When you open Claude a browser window should open and allow you to login. You should see the tools available in the bottom right. Given the right prompt Claude should ask to call the tool.
Deploy to Cloudflare
npx wrangler kv namespace create OAUTH_KV- Follow the guidance to add the kv namespace ID to
wrangler.jsonc npm run deploy
Call your newly deployed remote MCP server from a remote MCP client
Just like you did above in "Develop locally", run the MCP inspector:
npx @modelcontextprotocol/inspector@latest
Then enter the workers.dev URL (ex: worker-name.account-name.workers.dev/sse) of your Worker in the inspector as the URL of the MCP server to connect to, and click "Connect".
You've now connected to your MCP server from a remote MCP client.
Connect Claude Desktop to your remote MCP server
Update the Claude configuration file to point to your workers.dev URL (ex: worker-name.account-name.workers.dev/sse) and restart Claude
{
"mcpServers": {
"math": {
"command": "npx",
"args": [
"mcp-remote",
"https://worker-name.account-name.workers.dev/sse"
]
}
}
}
Debugging
Should anything go wrong it can be helpful to restart Claude, or to try connecting directly to your MCP server on the command line with the following command.
npx mcp-remote http://localhost:8787/sse
In some rare cases it may help to clear the files added to ~/.mcp-auth
rm -rf ~/.mcp-auth
Recommend MCP Servers 💡
@gitee/mcp-gitee
An MCP server for Gitee, enabling AI assistants to manage repositories, issues, and pull requests via Gitee's API.
k8s-mcp-server
K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI systems to assist with cluster management, troubleshooting, and deployments
Defang MCP Server
Defang is an AI-enabled cloud deployment platform that simplifies deploying applications to various cloud providers (AWS, GCP, DigitalOcean) with a single command, handling infrastructure complexities like security, scalability, and cost-efficiency.
gitlab-server
A TypeScript-based MCP server that interacts with a self-hosted GitLab instance, providing tools to fetch and manage GitLab projects, issues, notes, todos, and wiki pages.
openapi-mcp-server
Allow AI to wade through complex OpenAPIs using Simple Language
sentry-issues-mcp
An MCP server for Sentry issues, providing tools to retrieve single events or project events for LLM analysis