cuecaps-mcp
This MCP server lets you list Cuecaps caption styles, create preconfigured studio links, check account/plan minutes, transcribe local audio/video, and render captioned media locally with Cuecaps styles.
List the 10 caption styles with IDs, names, and visual descriptions (
list_styles).Generate a Cuecaps studio URL preconfigured with style, words/lines, position, aspect, and language (
studio_link).Check the linked account’s plan, remaining cloud minutes, reset date, and agent-captioning access (
account_status).Transcribe a local video/audio file into word-level timestamps plus SRT text, using cloud or on-device Whisper (
transcribe).Caption a local video/audio file and write output next to it: burned-in MP4, transparent MOV/WebM overlay, or SRT/VTT subtitles (
caption_video).Configure caption style, words per caption, lines, position, aspect ratio, language, keyterms, resolution, and FPS when captioning.
Use cloud transcription on plan minutes or on-device Whisper with no minutes; video rendering stays on your machine.
Return a studio link for fine-tuning words/style after captioning.
Uses ElevenLabs Scribe as the cloud transcription engine to produce timed words and SRT subtitles for video/audio files, consuming plan cloud minutes and supporting keyterms and automatic language detection.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
cuecaps-mcp
Caption a video or audio file on your computer from Claude Code, Cursor, Claude Desktop or any MCP client. Ask "caption
talk.mp4 in Karaoke and give me the MP4" and talk.captions.mp4 lands next to the original. The server drives the
Cuecaps studio's own export in headless Chrome or Edge on your machine, so the result matches a studio export of the same
settings. Once the project syncs to your account, caption_video also returns a studio link that opens it, to fix a word
or change the style.
No install: the hosted server
Apps that connect to an MCP server by URL can use https://cuecaps.com/mcp (Streamable HTTP) with no install and no
key: claude.ai and the Claude apps on phone and desktop, ChatGPT, Gemini CLI, Claude Code and Cursor. It has
list_styles and studio_link, so you ask for captions the way you'd describe them ("karaoke captions on a Spanish
TikTok") and get a studio link set up for them, to finish in your browser. To caption a file on your computer directly,
use this package (below).
claude.ai: Settings, Connectors, Add custom connector, and paste
https://cuecaps.com/mcp.Claude Code:
claude mcp add --transport http cuecaps https://cuecaps.com/mcpGemini CLI, in
~/.gemini/settings.json:{ "mcpServers": { "cuecaps": { "httpUrl": "https://cuecaps.com/mcp" } } }
Setup for every client: cuecaps.com/ai-assistants.
Related MCP server: faster-whisper-mcp
Requirements
Node 22 or later.
Google Chrome or Microsoft Edge, found at its standard install path.
CUECAPS_CHROMEpoints to any other browser.A key from cuecaps.com/account. Agent access comes with a Creator or Pro plan: cuecaps.com/pricing.
Setup
Claude Code
claude mcp add cuecaps --env CUECAPS_API_KEY=cck_… -- npx -y cuecaps-mcpClaude Desktop and Cursor
Add this to the MCP config: Settings, Developer, Edit Config in Claude Desktop, or ~/.cursor/mcp.json in Cursor.
{ "mcpServers": { "cuecaps": { "command": "npx", "args": ["-y", "cuecaps-mcp"], "env": { "CUECAPS_API_KEY": "cck_…" } } } }The Agent access card on cuecaps.com/account creates a key and shows this config with the key filled in.
Tools
Tool | Key | What it does |
| no | The 10 caption styles: id, name and how each one looks. |
| no | A studio link that opens set up with your settings. Works on every plan. |
| yes | Your plan, cloud minutes left this period, the date they reset, and whether it includes agent captioning. |
| yes | Every word of a file with its start and end time in seconds, plus the SRT text. Writes no file. |
| yes | Captions a file and writes the result next to it. |
Every input except path is optional. The caption settings use the studio-link names: style, words (1 to 10),
lines (1 or 2), position (top, middle, bottom), aspect (9:16, 1:1, 4:5, 16:9) and lang (a language
code such as es; auto lets cloud transcription detect it). Each tool's schema lists the valid values.
transcribe and caption_video also take:
engine:cloudis ElevenLabs Scribe on your plan's cloud minutes, strongest on music, accents and 90+ languages, and the default when the minutes left cover the file.deviceis on-device Whisper with no minutes; its first run downloads the model (132 MB). The result names the engine used.keyterms: up to 100 names and words for cloud transcription to spell your way.
caption_video also takes:
output:mp4with the captions burned in (the default),movorwebmas a transparent captions-only overlay, orsrtorvttsubtitles.resolution:720p,1080p(the default),1440por4k. 1440p and 4K come with Pro.fps: 24, 25, 30 (the default), 50 or 60.out_path: an absolute path in an existing folder to write to instead; its extension sets the output.
Examples
list_styles
{}Returns [{ "id": "bold", "name": "Bold", "look": "Montserrat in capitals with a black outline, …" }, …].
studio_link
{ "style": "karaoke", "words": 4, "aspect": "9:16" }Returns { "url": "https://cuecaps.com/studio?style=karaoke&words=4&aspect=9%3A16" }.
account_status
{}Returns { "plan": "creator", "minutes_left": 287.5, "resets": "2026-11-20", "agents": true }.
transcribe
{ "path": "/Users/ana/clips/talk.mp4", "engine": "device" }Returns { "words": [{ "text": "Greetings!", "start": 0.48, "end": 1.84 }, …], "srt": "1\n00:00:00,480 --> …", "engine": "device", "minutes_used": 0 }.
caption_video
{ "path": "/Users/ana/clips/talk.mp4", "style": "karaoke", "aspect": "9:16" }Returns { "file": "/Users/ana/clips/talk.captions.mp4", "duration": 17.17, "engine": "cloud", "minutes_used": 0.29, "studio_url": "https://cuecaps.com/studio#p=…" }.
While it runs, the server reports progress: Opening, Transcribing, Rendering 42%, Saving.
Output files
caption_video writes <name>.captions.<ext> next to the input. A file that already exists is never replaced: the
next run writes <name>.captions-2.<ext>, then -3, and so on. The same rule applies to out_path.
The studio link in studio_url opens the saved project on Creator and Pro. The video itself stays on your machine, so
the studio asks for the file again when you open the link on another device.
Settings
Variable | Use |
| Your key ( |
| Path to the Chrome or Edge executable, when it isn't at a standard install path. |
| The Cuecaps site, |
Privacy
Your video stays on your machine. The render happens in a browser on your computer.
Cloud transcription sends compressed speech audio, as the studio does, and deletes it after transcription.
engine: "device"sends no audio. The project and its words still sync to your account, as every project does on Creator and Pro.Your key goes only to
cuecaps.com/api/*requests. It is never in a URL, a log or a file.Each run uses a temporary browser profile and deletes it afterwards, so no cookies or projects stay behind.
License
MIT. The source is at github.com/Pantheonn3D/cuecaps-mcp.
Available Tools
5 toolsaccount_statusARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
caption_videoAInspect
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.
Inputs: path (required), fps, lang, lines, +9 more.
list_stylesARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
studio_linkARead-onlyIdempotentInspect
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.
Inputs: lang, lines, style, words, +2 more.
transcribeAInspect
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.
Inputs: path (required), lang, engine, keyterms.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
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.
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.
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.
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
Related MCP Connectors
Add burned-in captions to any video in one call: 28 caption styles, transcription, translation, dubbing, silence trimming and AI shorts. REST + MCP, prepaid credits (1 credit = 1 cent), free tools work without a key.
Add animated word-by-word captions (TikTok/Reels/Shorts style) to videos; get the captioned MP4.
Burn styled, word-timed karaoke captions into any video - captions API and MCP server for agents.
One call burns captions into your video. Hosted, prepaid, no subscription. MP4 plus SRT and VTT.
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables AI coding agents to programmatically assemble vertical videos and manage local CapCut Desktop drafts, including AI background removal, audio mastering to -14 LUFS or Demucs vocal isolation, music auto-ducking, punch zooms, karaoke captions, PiP proof overlays, hook badges, safe-zone linting, proxy previews, and EN→ES cloning/dubbing. It outputs real CapCut draft JSON ready for review and export.172MIT
- AlicenseNot gradedqualityCmaintenanceEnables local transcription of audio/video files and YouTube URLs, generation of SRT/VTT subtitles, and analysis of speech pacing and audience retention risk using faster-whisper.MIT
- AlicenseAqualityBmaintenanceEnables transcription of video speech and burning TikTok/Reels-style animated captions into MP4 files locally, using 15 preset styles with batch folder jobs and optional cloud transcription, correction, translation, and emoji features.12MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to generate animated overlays and edit short videos — cutting clips together, removing pauses, adding captions, and exporting overlays as MP4, MOV or WebM with transparent or green-screen backgrounds. All rendering, transcription and media handling happen locally on the user's own computer.11218 npmMIT