I gave my coding agent a sense of taste. It picks restaurants from my music

Description and use

The coding agent can now recommend restaurants that match the user’s music preferences by leveraging Qloo’s Taste API through a custom MCP server.

A coding agent can refactor code but cannot recommend restaurants based on personal taste.

The agent can now suggest restaurants that match the user’s music and film tastes, enabling personalized date planning.

1. Install and run the qloo-taste-mcp server with a QLOO_API_KEY.
2. Configure the agent’s .mcp.json to point to the server.
3. Use the provided tools (qloo_search, qloo_recommend, qloo_trending, qloo_tags) to query the taste graph.
4. The agent performs a cross-domain search: e.g., "I love Taylor Swift and Wes Anderson films — find me a restaurant in LA" → qloo_search for seeds → qloo_recommend for restaurants.

Qloo's Taste API sits on 250M+ cultural entities — music, movies, restaurants, brands, destinations — with a graph of how tastes connect.

I built qloo-taste-mcp: an MCP server that hands all of that to any agent as four tools.

Zero third-party dependencies — Python stdlib only. Without an API key the tools return a helpful error instead of crashing.

There's also a live demo in demo/ — Taste Match, a tiny web app where you search things you like, pick a category, and get recommendations.