Remote MCP Server on Cloudflare with Bearer Auth
This is a fork of https://github.com/cloudflare/ai/tree/main/demos/remote-mcp-server that removes the OAuth code and instead allows a Bearer Token to be passed in with the Authorization HTTP header.
In the MCP Inspector you can pass a Bearer Token like this:
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 - Under "Authentication" add your Bearer Token
- click "Connect"
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": {
"remote-example": {
"command": "npx",
"args": [
"mcp-remote",
"[https://remote.mcp.server/sse](http://localhost:8787/sse)",
"--header",
"Authorization: Bearer ${AUTH_TOKEN}"
]
},
"env": {
"AUTH_TOKEN": "..."
}
}
}
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": {
"remote-example": {
"command": "npx",
"args": [
"mcp-remote",
"[https://remote.mcp.server/sse](http://localhost:8787/sse)",
"--header",
"Authorization: Bearer ${AUTH_TOKEN}"
]
},
"env": {
"AUTH_TOKEN": "..."
}
}
}
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 💡
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
secureframe-mcp-server
This Model Context Protocol server provides read-only access to Secureframe's compliance automation platform for AI assistants like Claude and Cursor. It allows querying security controls, monitoring compliance tests, and accessing audit data across various frameworks such as SOC 2, ISO 27001, CMMC, and FedRAMP.
terraform-cloud-mcp
Integrates AI assistants with Terraform Cloud API for infrastructure management through natural conversation
tituslhy/sturdy-octo-fortnight
A MCP server integrating Jira and Confluence, providing API interaction tools via SSE transport
bitrise-io/bitrise-mcp
MCP Server for the Bitrise API, enabling app management, build operations, artifact management and more.
inspektor-gadget
AI-powered debugging and inspection for Kubernetes clusters using Inspektor Gadget.