mcpField
A
AI Engineer MCP 2025

AI Engineer MCP 2025

Local
ai-engineer-wf-2025.swyx-5de.workers.devOther55Updated 80w ago

About AI Engineer MCP 2025

AI Engineer MCP 2025 is a remote MCP server for the AI Engineer World's Fair 2025, built as a Cloudflare Worker. It also hosts the conference talk submission system. Users connect from an MCP client to ask about the conference.

Key features

  1. 01Remote MCP connection over an SSE endpoint
  2. 02Built as a Cloudflare Worker
  3. 03Includes a talk submission system
  4. 04Local debugging with MCP Inspector

Use cases

  1. 01Asking an MCP client about the conference
  2. 02Reference for structuring an MCP server on Cloudflare Workers
  3. 03Connecting Claude Desktop to a remote MCP server

MCP support

This project is an MCP server that exposes tools to MCP clients through an SSE endpoint. Clients connect by URL, optionally through mcp-remote.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"aie": {
"command": "npx",
"args": [
"-y",
"wrangler"
]
}
}
}
Run commandnpx -y wrangler

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmwrangler

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

AI Engineer MCP 2025

This project hosts the AI Engineer Conference 2025 talk submission system and MCP server.

Thanks to @threepointone for help setting this up with Cloudflare! <3

image

add this to your MCP Client

https://ai-engineer-wf-2025.swyx-5de.workers.dev/sse

// for example .cursor/mcp.json
{
  "mcpServers": {
    "AIECONF": {
      "url": "https://ai-engineer-wf-2025.swyx-5de.workers.dev/sse"
    }
  }
}

and then try "tell me about the conference" in your chat app that will then call the MCP server.

Project Structure

The project is built as a Cloudflare Worker with the following key components:

  • MCP server implementation in src/index.ts
  • Application logic in src/app.ts
  • Utility functions in src/utils.ts
  • Static assets in static/ directory

Develop locally

# clone the repository
git clone [email protected]:cloudflare/ai.git

# install dependencies
cd ai
npm install

# run locally
npx wrangler dev

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 SSE and enter http://localhost:8787/sse as 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!
MCP Inspector with the above config
MCP Inspector with after a tool call

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.

Clicking on the hammer icon shows a list of available tools
Claude answers the prompt 'I seem to have lost my calculator and have run out of fingers. Could you use the math tool to add 23 and 19?' by invoking the MCP add tool

Deploy to Cloudflare

  1. Make sure you have the following KV namespaces created:
    • OAUTH_KV for authentication
    • AIEWFSUBMISSIONS for talk submissions
  2. Ensure your secrets store is configured with the SECRETKEY
  3. Deploy using:
    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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.