Skip to main content
Glama

OpenSubtitles

Search subtitles

search_subtitles
Read-onlyIdempotent

Find subtitles for a movie or TV episode and get file_ids to download. Search by title (query), video filename, IMDb/TMDB/feature id with optional season/episode, or moviehash; filter by language and flags. Results are ranked with exact title, episode and release-name matches first.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_subtitles"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
typeNoRestrict to movies or TV episodes
yearNo
queryNoTitle to search for, e.g. "The Matrix". Not needed when an id, moviehash or filename is given.
imdb_idNoIMDb id (tt0133093 or 133093). With season_number/episode_number it is the show's id.
tmdb_idNoTMDB id. With season_number/episode_number it is the show's id.
filenameNoVideo filename, e.g. "Chicago.Fire.S14E01.1080p.WEB.h264-ETHEL.mkv". Parsed with guessit-js into title/year/season/episode; its release name ranks matching subtitles first.
order_byNorelevance = exact title/episode and release-name matches first, then popularityrelevance
per_pageNo
languagesNoSubtitle languages in order of preference, e.g. ["en", "pt-BR"]. Omit for all languages.
moviehashNoOpenSubtitles hash of the video file (calculate_file_hash in local mode). Exact file matches are flagged moviehash_match and ranked first.
feature_idNoOpenSubtitles feature id from search_features. With season_number/episode_number it is the show's id.
exact_titleNoWhen searching by title, first resolve it to the exact movie/show (so "The Matrix" does not return "The Matrix Revisited"). Set false for a fuzzy text search.
trusted_onlyNoOnly subtitles from trusted uploaders
season_numberNo
episode_numberNo
hearing_impairedNoSubtitles for the deaf and hard of hearing (SDH)include
foreign_parts_onlyNoSubtitles that only cover foreign-language dialogueinclude
include_ai_translatedNoInclude AI-translated subtitles
include_machine_translatedNoInclude machine-translated subtitles (usually low quality)

Output Schema

NameRequiredDescriptionDefault
pageYes
hintsYes
filtersYesEffective query sent to the OpenSubtitles API
guessedYesWhat guessit-js read from filename
resultsYes
per_pageYes
total_countYesMatches at the API for the effective filters
total_pagesYes
resolved_featureYesThe movie/show the title was resolved to, when exact_title applied

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, open-world and non-destructive behavior, so the bar is lower; the description still adds real value by disclosing the ranking model ('exact title, episode and release-name matches first'), which is not derivable from the annotations. It omits auth requirements and rate limits, so it is not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences with the core purpose front-loaded, followed by the lookup methods and then the ranking rule. No filler or repetition of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-shape explanation is unnecessary, and the description adequately covers the search modalities and ranking for a 20-parameter, zero-required tool. Minor gaps remain around whether multiple lookup keys can be combined and around paging behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 75% across 20 parameters, so the schema already carries most parameter meaning. The description usefully groups the mutually substitutable lookup keys and mentions language/flag filtering, but adds little beyond what the schema text already documents for individual fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource ('Find subtitles for a movie or TV episode') and states the outcome ('get file_ids to download'), which cleanly separates it from download_subtitle. It also enumerates the identification methods (query, filename, IMDb/TMDB/feature id, moviehash) so the agent knows what kind of search this is.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lays out the alternate lookup paths and the filter dimensions (language, flags), giving clear context for when each parameter family applies. It stops short of explicit exclusions or naming siblings to use instead (e.g., search_features for obtaining a feature_id), so it is clear but not fully routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.