Remote MCP Server on Cloudflare
A remote MCP server deployable 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
관련 서버
MCP Integration Suite Server
A ModelContextProtocol (MCP) server for interacting with the SAP Integration Suite.
Whissle AI
Provides speech-to-text, diarization, translation, and text summarization via the Whissle AI API.
Preloop
Preloop is an event-driven AI automation platform with built-in human-in-the-loop safety based on MCP proxying.
CData YouTube Analytics
An MCP server for accessing YouTube Analytics data, powered by the CData JDBC Driver.
Bigeye MCP Server
Interact with Bigeye's data quality monitoring platform via its Datawatch API. Supports dynamic API key authentication.
sentry-mcp-rs
A fast, lightweight MCP server for Sentry, written in Rust.
Bitrix24
The Bitrix24 MCP Server is designed to connect external systems to Bitrix24. It provides AI agents with standardized access to Bitrix24 features and data via the Model Context Protocol (MCP). The MCP server enables external AI systems to interact with Bitrix24 modules through a single standardized interface. You can connect the Bitrix24 MCP Server to the AI model you already use and manage Bitrix24 directly from it. The MCP server allows actions to be performed and data to be retrieved strictly within the access rights configured in your Bitrix24: the AI agent receives only the information and capabilities that are explicitly requested and authorized. Interaction with the Tasks module is supported (the list of supported modules and available actions is gradually expanding).
ServiceNow MCP Server
An MCP server for interfacing with ServiceNow, enabling AI agents to access and manipulate data via a secure API.
Codehooks.io
Integrate with the Codehooks.io serverless backend platform.
Rootly
Manage incidents on Rootly using your own API tokens via a Cloudflare Worker.