curator-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TMDB_API_KEY | No | Your TMDB API key for movie and TV metadata | |
| GOOGLE_BOOKS_API_KEY | No | Your Google Books API key for higher quota | |
| FIREBASE_CREDENTIALS_JSON | No | The Firebase service account JSON content as a string (alternative to FIREBASE_CREDENTIALS_PATH) | |
| FIREBASE_CREDENTIALS_PATH | No | Path to the Firebase service account JSON file | |
| FIREBASE_CREDENTIALS_BASE64 | No | Base64-encoded Firebase service account JSON (alternative to FIREBASE_CREDENTIALS_PATH) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_user_taste_profileA | Retrieve user taste profile including top genres, directors, authors, and highest-rated favorites. |
| get_entertainment_statsA | Get macro statistics across books, movies, podcasts, quotes, sensory vault, and restaurants. |
| get_agent_recommendation_briefC | Retrieve Taste DNA, anchor favorites, avoidances, and web search queries for a domain. |
| vet_recommendation_candidateC | Check a recommendation candidate for library collision and calculate taste affinity score. |
| search_vaultB | Unified search across all collections (books, media, sensory goods, restaurants, quotes). |
| search_booksC | Search books in Firestore by query and optional shelf ('read', 'currently-reading', 'to-read'). |
| get_reading_listB | Get books from user's reading queue ('to-read' or 'currently-reading'). |
| log_read_bookB | Log a completed book with rating (0-5 stars), optional review, and date read. |
| search_mediaC | Search movies and series in library by title, director, or genre. |
| get_watchlistB | Get movie and TV watchlist with optional type and genre filter. |
| log_watched_mediaC | Log watched movie or episode with rating (1-10), review, and date. |
| curate_for_tonightC | Filter watchlist by available time (minutes), genre, and IMDb rating. |
| log_sensory_itemC | Log or update an item in the Sensory Vault (tea, whiskey, coffee, wine, gin, perfume, watch). |
| search_sensory_vaultC | Search sensory vault items by keyword, category, rating, or flavor tag. |
| log_restaurantC | Log a restaurant or dining experience in dining journal or wishlist. |
| search_restaurantsB | Search dining vault by keyword, city, cuisine, status, or vibe tag. |
| get_aesthetic_pairingC | Generate aesthetic cross-domain pairing connecting books/movies with sensory beverages. |
| store_memoryC | Store a personal preference, habit, directive, or constraint in long-term memory. |
| recall_memoriesC | Recall stored memories and directives matching a topic or category. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| smart_recommendation_consultation | Orchestrate an internet-powered recommendation session with Taste DNA vetting. |
| daily_briefing | Generate a morning intellectual briefing with reading status, quote of the day, and wind-down pick. |
| tasting_session | Interactive sensory tasting interview to evaluate and log an artisanal item. |
| weekend_curation | Curate a weekend cultural itinerary (Film pick + Beverage pairing + Book reading + Dining spot). |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_taste_profile_context | Live background context resource providing Claude Desktop and agents with the user's taste preferences, 5-star books, 10/10 films, sensory flavor notes, and favorite cuisines. |
| get_active_queues_context | Live background context resource providing agents with currently reading books, movie watchlist items, and podcast queue. |
| get_daily_digest_context | Live background context resource providing a morning intellectual briefing: Quote of the Day, active reading metrics, and macro entertainment statistics. |
| get_taste_dna_dossier | Comprehensive Taste DNA dossier across literature, cinema, and culinary arts, including the user's cultural archetype analysis. |
| get_personal_memory_context | Active long-term personal memories, critical directives, habits, and constraints. |
TDQS
Scored across 19 tools
Most tools are clearly distinct (e.g., search_books vs search_media vs search_sensory_vault). However, search_vault is a unified search that overlaps with the domain-specific searches and get_reading_list with search_books (on shelf filter) could cause mild confusion. These overlaps are described but still require judgment.
Predominantly verb_noun (get_user_taste_profile, search_books, log_read_book), but some nouns are compound (search_sensory_vault, get_aesthetic_pairing). Minor deviations but overall predictable.
19 tools is slightly heavy but justifiable given the domain covers multiple verticals (books, media, dining, sensory, memory). Not excessive.
Covers logging and searching for most domains, but missing update/delete operations for some entities (e.g., no update_book, delete_media). Podcasts are mentioned in stats but no tools exist for them. Quotes also lack dedicated tools. These gaps could cause agent dead-ends.