DEV Community

hao li
hao li

Posted on Originally published at github.com

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

My coding agent can refactor a thousand lines without breaking a sweat, but ask it "where should I take a date Friday night" and it's useless. It knows my code. It knows nothing about my taste.

Qloo's Taste API sits on 250M+ cultural entities — music, movies, restaurants, brands, destinations — with a graph of how tastes connect. So I built qloo-taste-mcp: an MCP server that hands all of that to any agent as four tools.

Tool What it does
qloo_search Search the taste graph ("Taylor Swift", "ramen") → entity IDs
qloo_recommend Recommendations seeded by entity IDs — movies, restaurants, brands
qloo_trending What's trending in a category right now
qloo_tags Search the tag taxonomy (genres, cuisines, travel themes)

The fun part is the cross-domain jump: "I love Taylor Swift and Wes Anderson films — find me a restaurant in LA" → qloo_search for the seeds → qloo_recommend with urn:entity:restaurant. Taste transfers across categories, and the agent just follows the graph.

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

export QLOO_API_KEY=<your key>   # grab one at https://www.qloo.com
python3 -m qloo_taste_mcp.server
Enter fullscreen mode Exit fullscreen mode

With Claude Code, add to .mcp.json:

{
  "mcpServers": {
    "qloo": { "command": "python3", "args": ["-m", "qloo_taste_mcp.server"],
              "env": { "QLOO_API_KEY": "<your key>" } }
  }
}
Enter fullscreen mode Exit fullscreen mode

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. The API key never leaves the server (it binds 127.0.0.1, not 0.0.0.0).

18/18 tests pass, all HTTP-mocked. MIT licensed.

Built for the Qloo Agentic Hackathon.

Repo: https://github.com/hahahahahahahahah6/qloo-taste-mcp

If your agent suddenly developed opinions about ramen — what would you ask it first?

Top comments (0)