resto-mcp

resto-mcp

Searches restaurants via Google Places API and returns an interactive carousel, ready for Mistral Le Chat / Alpic.

Category
Visit Server

README

resto-mcp ๐Ÿ

MCP server that searches restaurants via Google Places and returns an interactive mcp-ui carousel. Streamable HTTP transport โ€” ready for Mistral Le Chat / Alpic.

Python 3.14 ยท FastMCP ยท uv

Live demo -> https://www.youtube.com/watch?v=2k0QMIKgt1g

Run locally

uv python install 3.14
uv sync --locked
cp .env.example .env   # add your GOOGLE_MAPS_API_KEY
uv run main.py         # POST http://localhost:3000/mcp

Enable Places API (New) on your Google Cloud project for the key.

Test with Mistral Vibe locally

Use ngrok to expose your local server for testing in Mistral Le Chat:

# One-time setup: authenticate ngrok (requires free account)
ngrok config add-authtoken <YOUR_AUTHTOKEN>  # Get it from https://dashboard.ngrok.com/get-started/your-authtoken

# Terminal 1: Start your server
MCP_HTTP_PORT=8001 uv run main.py

# Terminal 2: Expose it via ngrok
ngrok http 8001
# Copy the forwarding URL (e.g., https://abc123.ngrok.io)

In Mistral Le Chat:

  • Connectors โ†’ Add MCP โ†’ paste https://abc123.ngrok.io/mcp
  • Ask: "Where should I eat in Paris?" โ†’ carousel renders

Free ngrok accounts get a new random subdomain each time. Use ngrok http --subdomain=resto-mcp 8001 if you have a paid plan to keep a fixed URL.


Run automated tests

uv run pytest

Deploy on Alpic

  1. Push this repo to GitHub (private is fine).
  2. New project on Alpic โ†’ connect the repo โ†’ select the Python 3.14 runtime.
  3. Install: uv sync --locked ยท Start: uv run main.py (also in alpic.json).
  4. Env var: GOOGLE_MAPS_API_KEY
  5. Alpic gives you a public URL โ†’ your MCP endpoint is https://<that-url>/mcp

Note: MCP_ALLOWED_HOSTS is left unset on purpose. FastMCP ships with DNS-rebinding protection restricted to localhost, which would reject every request once the server sits behind a public domain. See .env.example.

Add to Mistral Le Chat

Connectors โ†’ add MCP โ†’ paste the https://<alpic-url>/mcp endpoint. Then ask: "Where should I eat in Paris 11e?" โ†’ the carousel renders automatically.

Team

  • Danny Antonelli
  • Andrea Gemelli
  • Lorenzo Santolini
  • Giulia Buzzetti

Tool

search_restaurants(location, limit?) โ†’ mcp-ui carousel + text fallback.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured