MCP server for searching and retrieving movie details from IMDb
Server has 4 tools with basic Zod schemas and descriptions, but significant gaps limit production readiness. Tool naming is inconsistent (search_and_play violates single-responsibility; imdb_search_title vs search_and_play are near-duplicates). Descriptions are present but generic (10-50 chars, below 194-char baseline). Parameter descriptions exist but lack constraints, ranges, or format guidance. Output schemas are undocumented, LLMs cannot predict response structure. Error handling is minimal (console.log only, no recovery guidance). No pagination support despite potential for large result sets. The play_movie and search_and_play tools both return URLs without structured metadata, forcing downstream parsing.
Get all items from a public IMDb list.
Search for movies, series, or games on IMDb.
Returns a playable URL for a movie or show using its IMDb ID
Directly returns the play URL for a searched movie or show.
Tool naming violates single-responsibility principle: search_and_play combines search + URL generation. Should split into separate tools or rename to clarify intent.
Duplicate/overlapping functionality: imdb_search_title and search_and_play both search IMDb. LLM cannot disambiguate when to use each. Consolidate or clearly document the distinction.
Output schemas undocumented. imdb_search_title returns JSON array with fields (imdb_id, title, year, type, starring, image) but LLM has no schema to predict structure. play_movie returns bare URL string without metadata.
Parameter descriptions lack constraints. titleTypes, sortBy, sortOrder, first have no range, enum values, or format guidance. LLM cannot validate inputs before calling.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | 2026-07-28+ | v2 |
No pagination support. imdb_search_title and imdb_get_public_list_items can return unbounded results. No limit parameter, no offset/cursor, no total count. Large result sets will exhaust context.