amodb-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AMODB_API_KEY | Yes | Your amodb API key. Required for tool calls. Without it the server starts, lists its tools, and every call returns an error. Get a key at https://amodb.dev/pricing. | |
| AMODB_BASE_URL | No | API base URL. Default `https://api.amodb.dev/3`. Mainly for tests. | https://api.amodb.dev/3 |
| AMODB_LANGUAGE | No | Default language for titles and overviews, for example `ru-RU` or `pt-BR`. A tool call can override it with `language`. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_titlesA | Search for movies, TV shows or people by name. Call this first when you have a title or a name and need the numeric id that the other tools require. Returns the best matches with id, title or name, release date, overview and popularity, at most |
| get_movieA | Get the full record of one movie by its numeric id: title, overview, runtime, genres, release date, budget, revenue, status and vote average. Use append to add related data in the same call: credits for cast and crew, videos for trailers, release_dates for age certifications, watch/providers for where to stream, external_ids for the IMDb and Kinopoisk ids, keywords, recommendations, similar and alternative_titles. The reviews section is empty for most titles. The amodb extras are also appended: ratings (imdb, kinopoisk, tmdb out of 10, metacritic and rotten_tomatoes out of 100, each as value and votes or null), moods (meters named action, fear, humor and so on, avg on a 0 to 10 scale, source measured or estimated), soundtracks (albums with tracks) and wikidata (budget, box office, sequels, awards, based_on). For cinema times use get_showtimes. Get the id from search_titles first. |
| get_tv_showA | Get the full record of one TV show by its numeric id: name, overview, genres, networks, status, number of seasons and episodes, and the list of seasons. Use append to add related data in the same call: credits for cast and crew, videos for trailers, content_ratings for age ratings, watch/providers for where to stream, external_ids for the IMDb, TVDB and Kinopoisk ids, keywords, recommendations, similar, alternative_titles and episode_groups. The reviews section and created_by are empty for most shows. The amodb extras moods, soundtracks, ratings and wikidata are also appended, with the same shapes as for movies. For cinema times use get_showtimes. Use get_season to list the episodes of one season. Get the id from search_titles first. |
| get_seasonA | Get one season of a TV show with its full episode list: episode number, name, air date, runtime, overview and vote average for each episode. Use it to answer questions about episodes, air dates or season length. Season number 0 holds the specials. You need the TV show id from search_titles or get_tv_show. |
| get_personA | Get the record of one actor, director or other crew member by numeric id: name, biography, birth and death dates, place of birth and known department. Use append to add combined_credits for the full filmography (movies and TV together), movie_credits or tv_credits for one kind, images for photos, or external_ids for the IMDb id. Get the id from search_titles with media_type person. |
| find_by_external_idA | Look up a movie, TV show or person by an id from another system, when you do not have the amodb numeric id. Typical use: the user gives an IMDb id such as tt0137523 (titles) or nm0000093 (people), a Kinopoisk id (digits), or a Wikidata id (Q followed by digits). Returns movie_results, tv_results and person_results, each item with a media_type; take the id from the matching list and pass it to get_movie, get_tv_show or get_person. The result also has tv_episode_results and tv_season_results, which are always empty. A missing or unknown external_source, or a malformed id, is an error. |
| trendingA | List what is trending now: movies, TV shows, people, or all three mixed. Use it for questions like "what is popular today" or "what are people watching this week". Returns at most |
| discover_moviesA | Find movies by filters instead of a name: genre, release year, minimum rating, original language, region and sort order. Use it for requests like "best rated sci-fi from 2010" or "popular French comedies". Returns at most |
| get_showtimesA | Find where and when a movie or TV title is showing in cinemas, from today on. Without country the reply lists the countries that have showtimes, each with counts of venues, cities and showtimes and the first and last day, most showtimes first; results is then empty. Call it again with a two letter country code (for example RU) to get the cinemas: name, chain, city, address, timezone, and per showtime the local start time, date, formats, auditorium, price and booking_url. Start times are local to the cinema. Output is limited to the first |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct input type and resource: name search, id-based detail retrieval, external-id lookup, trending, filter discovery, and cinema showtimes. Overlaps such as search_titles versus discover_movies are explicitly separated by description (name vs. filters), so misselection is unlikely.
Eight of nine tools follow a consistent snake_case verb_noun or verb_preposition_noun pattern (search_titles, get_movie, get_tv_show, find_by_external_id, etc.). 'trending' is a lone noun without a verb, but it is still readable and no mixed conventions appear.
Nine tools is well within the effective range for a read-only media metadata API. Each tool covers a distinct capability, with no obvious filler or redundancy.
The surface covers the core read lifecycle: search, detail by id, external-id fallback, trending, filter discovery, seasons/episodes, people, and showtimes. A TV-specific discover tool and standalone episode-by-id lookup are missing, but agents can work around these via get_tv_show and get_season.