Remote MCP Server on Cloudflare
Deploy a remote MCP server on Cloudflare Workers with OAuth login support, using Cloudflare KV for data storage.
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 https://github.com/cloudflare/ai.git
# Or if using ssh:
# git clone [email protected]:cloudflare/ai.git
# install dependencies
cd ai
# Note: using pnpm instead of just "npm"
pnpm 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
Похожие серверы
Code Ocean MCP Server
Search and run capsules, execute pipelines, and manage data assets on the Code Ocean platform.
Arc MCP Server
Simplifies framework deployments on various hosting environments, with a focus on shared hosting.
IPGeolocation.io MCP Server
Official MCP server for IP geolocation, IP security, abuse contacts, ASN, timezone, astronomy, and user-agent parsing.
CData Twitter Ads
An MCP server for accessing Twitter Ads data, powered by the CData JDBC Driver.
MiniMax MCP
Interact with MiniMax's powerful Text-to-Speech, image, and video generation APIs.
SafetyCulture MCP Server
Ask natural language questions about your SafetyCulture data using the SafetyCulture API.
Weather
Accurate weather forecasts via the AccuWeather API (free tier available).
CoinMarketCap MCP
Access cryptocurrency market data, exchange information, and other blockchain-related metrics from the CoinMarketCap API.
Datadog MCP Server
Provides comprehensive Datadog monitoring capabilities through MCP clients. Requires Datadog API and Application keys.
PlayFab MCP Server
A middleware server that allows large language models to interact directly with PlayFab services.