Taste-based film, TV, book and game picks: similar in feel, taste reads, picks for two.
Scored across 5 tools
Each tool has a fairly distinct role: catalogue lookup, single-title profile, single-title similarity, two-person matching, and multi-title personal reading. The one soft boundary is between find_similar_in_feel and quick_taste_read, since both return suggestions, but their inputs and outputs are described clearly enough to distinguish.
All names are lowercase snake_case, which helps, but the conventions are mixed: find_similar_in_feel and get_title_taste_profile are verb-led, search_titles is verb_noun, match_for_two is verb-preposition-number, and quick_taste_read is adjective-led. Readable overall, but not a predictable pattern.
Five tools is well scoped for a taste-based discovery server. Each tool maps to a distinct user intent and there is no obvious filler.
The set covers lookup, title-level taste explanation, similarity search, two-person matching, and personal taste readings, which is strong lifecycle coverage for discovery. Minor gaps remain, such as browsing or filtering the catalogue directly by taste dimension/theme rather than always starting from specific titles.
Titles that feel like a given film, TV series, book or game — matched on Boxlist's taste dimensions, story themes and subjects, not just genre or cast — across all four media or only the ones you choose. Each result says what it shares with the starting title. Good for "I loved X, what next?" and cross-media asks like "a book that feels like Succession".
Inputs: title (required), limit, media, titleMedia. Returns: note, seed, method, results, +4 more
How a film, TV series, book or video game feels, in plain words: its scores on Boxlist's ten taste dimensions (pace, originality, wholesomeness, weightiness, realism, intricacy, linearity, style, scale, emotional punch), its story themes and the Taste Type it suits. For films and TV it adds where to watch in the UK and US; for games, platforms and stores. Use it to explain why someone might or might not enjoy a title.
Inputs: title (required), year, media. Returns: title, genres, summary, nextStep, +10 more
Find titles two people will both enjoy, from one to five titles each of them loves. Blends their two Taste Fingerprint™ profiles the way Boxlist's Watch together does, skips anything either is likely to dislike, and returns picks with a band for the pair and for each person, plus where their tastes agree and differ. Defaults to films and TV; books and games can be added. Anonymous, nothing stored.
Inputs: personA (required), personB (required), limit, media, +1 more. Returns: picks, personA, personB, privacy, +3 more
Turn 2 to 5 titles someone loves (films, TV, books or games, mixed is fine) into a short Taste Fingerprint™ reading — their leans on Boxlist's taste dimensions, their Taste Type and recurring themes — plus suggestions with a Boxlist match band and a reason for each. Anonymous: no account, nothing stored. Use it for "what should I watch/read/play, I like X, Y and Z".
Inputs: lovedTitles (required), limit, media, suggestFrom. Returns: privacy, nextStep, understood, attribution, +2 more
Find films, TV series, books and video games in the Boxlist catalogue by name (books also by author). Returns each title's boxlist.com page and a ref to pass to the other Boxlist tools. Use it to pin down the right title (e.g. which "Dune") before asking for a taste profile or similar titles.
Inputs: query (required), limit, media. Returns: note, query, results, nextStep, +1 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Pick one movie, show, book, artist or restaurant a whole group will enjoy, using Qloo taste data.
Personalised book recommendations, filtered to what's on your public library's shelf right now.
Books like one you enjoyed, a book's details and any film of it, and an author's books.
Picks from real people for things to buy, watch, read, eat or do, each with a working store link.
Add one secure layer between your agents and this server.