tmdb-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TMDB_REGION | No | Default country for watch providers and `streamingOn` | US |
| TMDB_API_KEY | No | v3 key, used only if no read access token is set | |
| MCP_HTTP_HOST | No | HTTP mode only: host to bind | 127.0.0.1 |
| MCP_HTTP_PORT | No | HTTP mode only: port to bind | 3000 |
| TMDB_LANGUAGE | No | Language of titles and overviews | en-US |
| TMDB_TIMEOUT_MS | No | Per-request timeout in milliseconds | 10000 |
| TMDB_MAX_RETRIES | No | Retries on 429/5xx | 3 |
| MCP_HTTP_AUTH_TOKEN | No | Required in HTTP mode. Bearer token for `POST /mcp` authentication. | |
| TMDB_CACHE_MAX_ENTRIES | No | LRU eviction above this number of entries | 500 |
| TMDB_CACHE_TTL_SECONDS | No | Cache TTL in seconds. `0` disables the cache | 600 |
| TMDB_READ_ACCESS_TOKEN | No | v4 token (preferred), sent as a bearer header. Get one at https://www.themoviedb.org/settings/api | |
| MCP_HTTP_RATE_LIMIT_PER_MINUTE | No | HTTP mode only: per client IP rate limit. `0` disables | 60 |
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
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_moviesA | Find movies by title (fuzzy). Returns ids to use with get_movie_details, get_recommendations and get_watch_providers. Pass |
| search_tv_showsA | Find TV series by name (fuzzy). Returns ids to use with get_tv_show_details and other tools. |
| search_peopleA | Find actors, directors and other crew by name. Returns ids to use with get_person_details. |
| get_movie_detailsA | Full details for one movie in a single call: runtime, genres, score, directors, writers, top cast, budget, revenue and trailer. |
| get_tv_show_detailsA | Full details for one TV series: status, seasons, episodes, networks, creators, top cast and score. |
| get_person_detailsA | Biography and the 15 best-known movies/shows of an actor or crew member, with the role they had in each. |
| get_watch_providersA | Where a movie or show can be streamed, rented or bought in a country. Data comes from JustWatch; mention that source when showing it to users. |
| discoverA | Find titles by criteria instead of by name: genres (by name, e.g. "sci-fi", "comedy"), year range, minimum score, max runtime, original language and streaming service (e.g. "Netflix") in a country. Best tool for requests like "a good 90s thriller on Netflix under 2 hours". |
| get_trendingB | What is trending on TMDB today or this week: movies, TV shows, people, or all of them mixed. |
| get_recommendationsA | Titles that people who liked a given movie or show also liked. Use for "something like X" requests; combine with get_watch_providers to check availability. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| movie_night | Pick three movies for a group, available on the streaming services they have |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| genres | Valid genre names for movies and TV shows, as accepted by the discover tool |
TDQS
Scored across 10 tools
Each tool targets a distinct intent: search_* tools find by name for a specific resource type, discover browses by filters, and the get_* tools each retrieve details for a specific resource. discover vs search_movies and get_recommendations vs discover are the closest overlap but descriptions clearly delineate criteria-based browsing from name lookup and 'more like X' requests.
Consistent verb_noun pattern across search_movies, search_tv_shows, search_people, get_movie_details, get_tv_show_details, get_person_details, get_watch_providers, get_trending, and get_recommendations. The lone outlier is the bare-verb 'discover', a minor deviation.
Ten tools is well-scoped for a media discovery domain, with search, details, discovery, trending, recommendations, and availability each earning a distinct slot without redundancy.
The surface covers the core lifecycle: finding titles/people, browsing by filters, fetching details, watching providers, trending, and recommendations. Minor gaps exist around season/episode-level detail and collection/list operations, but agents can work around these.