Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
YT_SUB_MCP_CACHENoSet to '0' to disable the disk cache layer.1
YT_SUB_MCP_CACHE_DIRNoDirectory to store the cache. Default: on macOS ~/Library/Caches/yt-sub-mcp/, otherwise $XDG_CACHE_HOME/yt-sub-mcp/.
YT_SUB_MCP_CACHE_TTL_DAYSNoCache entry expiration in days. '0' means no expiration.30

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_subtitle_tracksA

List the subtitle tracks available for a video.

Use this when unsure which languages exist, or whether captions are human-written or auto-generated.

get_subtitlesA

Read a video's subtitles as text.

Returns human-written captions when they exist, otherwise the
auto-generated track. Output is truncated at `max_chars`; when that
happens the response ends with the timestamp to resume from, which
you pass back as `start_time` to read on.
search_subtitlesA

Find where a phrase is said in a video.

Cheaper than reading the whole transcript: returns matching passages
with timestamps and deep links. Follow up with `get_subtitles` and a
time range to read a hit in full.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.3/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clear, distinct role: list tracks, read subtitles, and search within them. There is no overlap or ambiguity between the three operations.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (list_, get_, search_). The naming is uniform and predictable, with no mixed conventions.

Tool Count5/5

Three tools is well-scoped for a YouTube subtitles server, covering the essential operations without unnecessary bloat. Each tool serves a necessary function.

Completeness4/5

The core operations of listing, reading, and searching subtitles are all present. A minor gap is the lack of an explicit way to select a specific subtitle track by language or ID, as get_subtitles appears to auto-pick human-written captions.

Maintenance

ActivitySlowing
ResponsivenessNo issues