Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CUECAPS_URLNoThe Cuecaps site URL.https://cuecaps.com
CUECAPS_CHROMENoPath to the Chrome or Edge executable, when it isn't at a standard install path.
CUECAPS_API_KEYNoYour Cuecaps API key (starts with `cck_` and is 32 characters). Needed for captioning; list_styles and studio_link work without it.

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
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_stylesA

Lists the 10 Cuecaps caption styles, each with the id to pass as style to caption_video or studio_link, its name and how it looks. The list is fixed and needs no key. Call it when the user hasn't picked a style or asks what the styles look like.

studio_linkA

Returns a URL to the Cuecaps studio, opened with these caption settings, for the user to finish in their browser: they drop in the video, can fix words and export there. Creates nothing and needs no key, so it works on every plan, Free included. Use it when the user wants to edit by hand, has no Creator or Pro key, or the file isn't on this machine; use caption_video to make the file directly.

account_statusA

Reads the Cuecaps account behind CUECAPS_API_KEY: the plan, cloud minutes left this period, the date they reset, and whether agent captioning is included. Uses no minutes. Call it before transcribe or caption_video to check the plan and minutes; with no key or an invalid key it returns an error that says how to get one.

transcribeA

Transcribes a local video or audio file and returns every word with its start and end time in seconds, plus the SRT text and the engine used. Writes no file: use caption_video when the user wants a captioned video, an overlay or a subtitle file. Needs a Creator or Pro key. engine "cloud" uses the plan's minutes and sends only compressed audio, deleted after transcription; "device" runs Whisper locally and uses none. Left unset, it picks cloud when the minutes left cover the file, else device.

caption_videoA

Captions a local video or audio file with the Cuecaps studio's renderer in headless Chrome or Edge and writes .captions. next to it, never replacing a file: an MP4 with the captions burned in, a transparent MOV or WebM overlay, or SRT or VTT subtitles. Returns the file, its duration in seconds, the engine, the cloud minutes used and a studio link to fine-tune words and style. Needs a Creator or Pro key; 1440p and 4K need Pro. Transcription works as in transcribe, and the video never leaves this machine. Use transcribe when only the words are needed, and studio_link when the user wants to edit by hand or has no key.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a clearly distinct purpose: listing styles, reading account status, generating a studio URL, transcribing to text, and rendering a captioned file. The descriptions explicitly cross-reference when to use one versus another (e.g. transcribe vs caption_video vs studio_link), leaving no realistic ambiguity.

Naming Consistency3/5

The set mixes patterns: verb_noun (list_styles, caption_video), a bare verb (transcribe), and noun_noun phrases (account_status, studio_link). Names remain readable and individually clear, but there is no single predictable convention.

Tool Count5/5

Five tools is well-scoped for a captioning service, and each covers a necessary step in the workflow: discover styles, check quota, transcribe, render captions, or hand off to the studio. No tool feels redundant or missing at this count.

Completeness4/5

The surface covers the core lifecycle: style discovery, account/quota check, text-only transcription, final caption rendering, and browser handoff. Minor gaps exist around managing or retrieving past outputs or batch/URL-based inputs, but the main workflows are reachable.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues