mcp-cinema
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGORA_HOME | No | The directory where the index is stored. If set, the LanceDB index is expected at $AGORA_HOME/lancedb. Defaults to ./data (i.e., data/lancedb). |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_filmsA | Recherche sémantique de films par intrigue, thème ou ambiance. |
| get_filmA | Retourne la fiche complète d'un film (synopsis intégral), à partir du film_id de search_films. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| trouver-un-film | Retrouve un film à partir d'une scène, d'une intrigue ou d'un souvenir flou. |
| recommander-des-films | Des films qui correspondent à une envie, avec un genre et une période optionnels. |
| fiche-film | L'intrigue d'un film précis, lue dans son synopsis complet. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| archives_cinema | Étendue des synopsis indexés, outils disponibles et exemples de questions. |
TDQS
Scored across 2 tools
get_film and search_films have clearly distinct purposes: one retrieves full details by film_id, the other performs semantic search by query and filters. The descriptions explicitly link them (get_film uses film_id from search_films), leaving no ambiguity.
Both names follow a consistent snake_case verb_noun pattern: get_film and search_films. The convention is predictable and readable throughout.
Two tools is thin for a cinema domain, even if the server is intentionally minimal. It covers search and retrieval but lacks other common operations (e.g., listing genres, getting people, or browsing without a query), making the set feel under-scoped.
The core read-only workflow is covered: semantic search with filters and full film details by ID. Minor gaps exist (e.g., no way to list films without a query or explore related entities), but agents can work around them for the stated purpose.