Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Food Order Bot MCP ServerWhat are your best-selling pizzas? Add a Margherita to my cart."
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.
Food Order Bot MCP Server
This directory contains a standalone MCP server that exposes the Food Order Bot's capabilities (Menu Guide & Order Management) to MCP clients (like Claude Desktop, Cursor, etc.).
Setup
Navigate to this directory:
cd MCPInstall Dependencies:
pip install -r requirements.txtEnvironment Variables:
Ensure
.envis present in this directory with the following keys:MONGO_URIDATABASE_URL(optional, for pool)GOOGLE_API_KEY
Running the Server
Run the server using the mcp-cli or python directly if using FastMCP's built-in runner:
python server.py
# MD: mcp run server.pyAvailable Tools
menu_guide(query, tenant_key, session_id): Browse menu, ask for recommendations.order_management(query, tenant_key, session_id): Add/Remove items from cart.
Directory Structure
server.py: Main entry point, defines MCP tools.utils.py: Minimal utilities for DB and LLM connection (stripped of heavy framework deps).tools/: Refactored tool logic (copied from main project but using local utils).
This server cannot be installed
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.