Remote MCP Server (Authless)
# Building a Remote MCP Server on Cloudflare (Without Auth)
https://remote-mcp-server-authless.feraranas.workers.dev/
<details>
<summary>Good to know & read Docs</summary>
# Building a Remote MCP Server on Cloudflare (Without Auth)
This example allows you to deploy a remote MCP server that doesn't require authentication on Cloudflare Workers.
## Get started:
[](https://deploy.workers.cloudflare.com/?url=https://github.com/cloudflare/ai/tree/main/demos/remote-mcp-authless)
This will deploy your MCP server to a URL like: `remote-mcp-server-authless.<your-account>.workers.dev/sse`
Alternatively, you can use the command line below to get the remote MCP Server created on your local machine:
```bash
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
```
## Customizing your MCP Server
To add your own [tools](https://developers.cloudflare.com/agents/model-context-protocol/tools/) to the MCP server, define each tool inside the `init()` method of `src/index.ts` using `this.server.tool(...)`.
## Connect to Cloudflare AI Playground
You can connect to your MCP server from the Cloudflare AI Playground, which is a remote MCP client:
1. Go to https://playground.ai.cloudflare.com/
2. Enter your deployed MCP server URL (`remote-mcp-server-authless.<your-account>.workers.dev/sse`)
3. You can now use your MCP tools directly from the playground!
## Connect Claude Desktop to your MCP server
You can also connect to your remote MCP server from local MCP clients, by using the [mcp-remote proxy](https://www.npmjs.com/package/mcp-remote).
To connect to your MCP server from Claude Desktop, follow [Anthropic's Quickstart](https://modelcontextprotocol.io/quickstart/user) and within Claude Desktop go to Settings > Developer > Edit Config.
Update with this configuration:
```json
{
"mcpServers": {
"calculator": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse" // or remote-mcp-server-authless.your-account.workers.dev/sse
]
}
}
}
```
Restart Claude and you should see the tools become available.
</details>
TDQS
Scored across 2 tools
The two tools 'add' and 'calculate' are highly ambiguous without descriptions, as 'add' could be a subset of 'calculate' or vice versa, making it impossible to distinguish their purposes. This overlap creates a high risk of misselection, as agents cannot determine when to use one over the other based on the limited information provided.
The tool names 'add' and 'calculate' are both simple verbs, which provides some readability, but they lack a consistent pattern such as verb_noun or clear domain-specific conventions. The naming is mixed in style, with 'add' being a basic operation and 'calculate' being more general, but without descriptions, it's unclear if this reflects intentional design or inconsistency.
With only 2 tools, the server feels thin and under-scoped for most practical purposes, suggesting it may not cover a meaningful domain adequately. This low count is borderline inappropriate unless the server's purpose is extremely narrow, but without descriptions, it's hard to justify such minimalism, leaning toward too few tools for effective agent use.
The server is severely incomplete, as the lack of descriptions makes it impossible to infer a domain or assess coverage. With only vague tool names like 'add' and 'calculate', there are obvious gaps in any potential workflow, and agents will likely fail due to missing operations or unclear scope, rendering the tool surface non-functional for typical tasks.