gogo-backend-mcp
A FastMCP-powered server for accessing curated travel spot data from a PostgreSQL database. It provides tools to retrieve major attractions, supporting sites, and the top ten most popular destinations.
README
gogo-backend-mcp
A lightweight MCP-powered backend for serving curated travel spots straight from model.spot. The FastMCP server in trip.py exposes tools that let any compatible client request the latest main attractions, supporting sites, and the top ten most popular destinations.
Features
major_views,sub_views, andtop_10_spotstools implemented via FastMCP.- SQLAlchemy ORM mapped through
model/spot.pywith GeoAlchemy spatial support. - Environment-driven configuration with
.envplus sensible defaults inutil/database.py.
Requirements
python -m pip install -r requirements.txt
Environment
Copy .env.example (if you create one) or create a .env file with at least:
DATABASE_URL=postgresql+psycopg://user:password@localhost/spot_db
LOG_LEVEL=INFO
util/database.py will fall back to postgresql+psycopg://postgres:password@localhost/spot_db when nothing is provided.
Database
- The app expects a PostgreSQL database with a
public.spottable matchingmodel.spot.Spot. - The table requires the PostGIS extension for the
locationgeometry column. - Apply your own migrations or schema creation outside this service; SQLAlchemy will not auto-create tables here.
Running locally
python trip.py
The MCP server listens on stdio and exposes three async tools:
major_views– active spots withpopularity > 3000.sub_views– active spots with1 < popularity < 3000.top_10_spots– ten most popular active spots.
Each tool returns JSON data from the respective helper in src/action.py.
Logging
util/logging_setup.py configures a single console handler; change LOG_LEVEL or wrap calls with your own handlers if you need file logging.
MCP Setup
This project uses FastMCP to create an MCP server. The server exposes three tools that clients can call to retrieve travel spot data.
{
"servers": {
"trip-mcp": {
"command": "uv",
"args": [
"--directory",
"/{Project Parent Location}",
"run",
"trip.py"
],
"env": {
}
}
// add your MCP stdio servers configuration here
// example:
// "my-mcp-server": {
// "type": "stdio",
// "command": "my-command",
// "args": [],
// "env": {
// "TOKEN": "my_token"
// }
// }
}
}
#� �g�o�g�o�-�b�a�c�k�e�n�d�-�m�c�p�6� � �
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.