How do I use Guess Number MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Guess Number MCP Server start a new game for me" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Guess Number MCP Server (Remote)

This project implements a remote MCP (Model Context Protocol) server for a simple number guessing game. The server is deployed on Google Cloud Run and allows a client chatbot to interact with it using JSON requests.

The server tracks game state per user and keeps a log of conversations.

Project Structure

│── server/ │ └── mcp_server.py # FastAPI server for the guessing game │── requirements.txt # Python dependencies │── Dockerfile # Container configuration for Cloud Run

Configuration

Clone the repository:

git clone [<your-repo-url>](https://github.com/DiegoDuaS/MCP-Remote) cd MCP-Remote

Install dependencies (for local testing):

pip install -r requirements.txt

Running Locally

To run the server locally on port 8080:

python server/mcp_server.py

Access the endpoint at:

POST http://127.0.0.1:8080/guess

JSON body format:

{ "user_id": "default_user", "message": "start" }

Deploying to Google Cloud Run

Build the Docker image:

gcloud builds submit --tag gcr.io/<PROJECT_ID>/guess-game

Deploy to Cloud Run:

gcloud run deploy guess-game \ --image gcr.io/<PROJECT_ID>/guess-game \ --platform managed \ --region us-central1 \ --allow-unauthenticated \ --port 8080

The server will be available at:

https://<SERVICE_NAME>-<PROJECT_NUMBER>.us-central1.run.app/guess