Cupcake

Provides an MCP server with two tools (search and fetch) to discover and retrieve cupcake orders for ChatGPT on Wasmer Edge.
  • python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

This Cupcake MCP Server runs a Model Context Protocol (MCP) server for ChatGPT and connects through Wasmer Edge. It exposes two practical tools, search and fetch, enabling ChatGPT to discover cupcake orders and retrieve full details on demand. You can run it locally for testing and deploy it to Wasmer Edge for production use.

How to use

Connect your MCP client (ChatGPT with MCP enabled) to the server endpoint and start querying it for cupcake data. You will have two tools available: search to find cupcake orders by keywords, and fetch to retrieve complete details for a specific order ID. For example, you can ask to count orders, look up items by flavor, or fetch all details for a given order.

Usage pattern you can follow is to first search with a query like a flavor, a customer name, or a date, then pick a matching result and fetch its full details by ID. The server serves data loaded from a records.json file and exposes the two tools via MCP so your client can discover and retrieve items efficiently.

How to install

Prerequisites you need before running the server: a Python 3.x environment and pip for package management.

# Install required Python dependencies
pip install -r requirements.txt

# Run the server locally
python server.py

Additional sections

Deployment to Wasmer Edge provides a hosted MCP endpoint for production access. Include both the server script and its data file in your project, deploy to Wasmer Edge, and set the entry point to the server script. Once deployed, you will receive an accessible URL to connect from your MCP client.

Server details at startup: the server uses Server-Sent Events (SSE) to communicate MCP events and responses to the client. The server exposes two MCP tools: search and fetch. The search tool splits your query into tokens and matches them against the records’ title, text, and metadata. The fetch tool returns full order details by ID, including optional URL and metadata.

Example usage you can try after deployment: use search("red velvet") to see matching cupcake orders, then use fetch("42") to retrieve the complete details for that order.

Available tools

search

Searches cupcake records by query tokens and returns a list of matching results, scanning title, text, and metadata.

fetch

Retrieves full details for a cupcake order by ID, including optional URL and metadata.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational