MCP App Store
by KeenEthics
Shorty icon

Shorty MCP Server for Claude and ChatGPT

By Devino Solutions

Overview

Shorty turns long videos, audio files, documents and web pages into readable summaries and accurate transcripts. The Shorty connector lets Claude work with that library from your own account: search your summaries, open a specific article and read its highlights and body, list what you made recently, list and open your transcriptions, check how much of your plan's quota is left, and search Shorty's developer documentation. It can also start new work - summarize a YouTube link, a web page, pasted text or a file already uploaded to your Shorty account; transcribe a publicly accessible audio or video URL; and add subtitle tracks to a video you provide. Claude reaches these through two tools, search_tools and execute_typescript. These are long-running jobs, not instant answers. A write tool returns a job id, and Claude polls get_job_status until the job reaches SUCCESS, ERROR or CANCELLED before fetching the finished article or transcript. Over the connector Shorty returns job handles and text, never a media file, and subtitle files are downloaded from the Shorty app, not from the chat. Write tools are backed by an idempotency ledger, so a retried request will not create a duplicate job, and no tool here deletes or overwrites work you already have. Access runs through OAuth 2.1 with PKCE. You choose which scopes to grant on the consent screen - separate read scopes for articles, transcriptions, jobs, usage and docs, and separate write scopes for creating summaries and transcriptions - and any tool whose scope you did not grant is never offered to Claude at all. Consent is re-checked on every individual tool call, so revoking Shorty from Settings > Connected AI Apps stops the assistant on its very next call, not at token expiry. Summaries and transcriptions draw on your Shorty plan's monthly quota, and Claude can read the balance with get_usage_quota before starting a long job. Nothing is sold in chat, no images, video or audio are generated, and no ads are served.

How to connect

  1. Claude: Open the Shorty listing in the Claude connectors directory and choose Connect. Claude listing Shorty exposes 2 tools here.
  2. ChatGPT: Open the Shorty listing in the ChatGPT app directory and choose Connect. ChatGPT listing Shorty exposes 17 tools here.

Tools

create_content_summary

ChatGPT
Start an AI summary job for a webpage URL, pasted text, or a file already uploaded to Shorty. Supply exactly ONE source field, and it must be the one the sourceType reads: 'webpage'/'article' → url; 'text' → text; 'pdf'/'word'/'audio' → fileKey. Those last three read an already-uploaded file and NEVER accept a url — a link to a PDF cannot be summarized here, the file has to be uploaded first. Returns { jobId, articleId? }. If articleId is present the summary already exists — read it with get_article; get_job_status on that jobId also reports SUCCESS with outputId. Otherwise poll get_job_status. Pass a stable idempotencyKey to make retries safe.

create_subtitles

ChatGPT
Generate subtitles for a public video/audio URL. Style is CLEAN | TIKTOK | PODCAST | MINIMAL; not every style is included in every plan, and CLEAN always is. Returns { jobId, trackingUrl } — poll get_job_status; the user can download SRT/VTT, and a captioned MP4 where their plan includes it. If the account has reached a plan limit the call is denied with a message naming the limit — report that message as-is. Call get_usage_quota for the account's actual limits and remaining usage. Pass a stable idempotencyKey to make retries safe.

create_transcription

ChatGPT
Transcribe a publicly accessible audio/video URL via the GPU service. Returns { jobId, trackingUrl } to follow, or an { error } if it did not start (relay that reason and suggest uploading the file instead). Poll progress with get_job_status. Pass a stable idempotencyKey to make retries safe.

create_youtube_summary

ChatGPT
Start an AI summary job for a YouTube URL. Returns { jobId, articleId? }. If articleId is present the summary already exists — read it with get_article; get_job_status on that jobId also reports SUCCESS with outputId. Otherwise the job started — poll it with get_job_status. Pass a stable idempotencyKey to make retries safe (a repeat returns the original job).

execute_typescript

ChatGPT
Run a short TypeScript program that orchestrates Shorty MCP tools (found via search_tools) in an isolated sandbox. See the server instructions for the full contract.

get_article

ChatGPT
Fetch a single article (summary, highlights, body) so you can answer questions about it. Pass a real article UUID as articleId.

get_article_source_download

ChatGPT
A single-use link to the source file or original transcript behind one of the user's summaries.

get_job_status

ChatGPT
Check the status of a job you started (summary, transcription, or subtitles) by its jobId. Returns { found, status, jobType, outputId? }: status is QUEUED | PROCESSING | SUCCESS | ERROR | CANCELLED. Poll until terminal (SUCCESS/ERROR/CANCELLED).

get_subtitle_download

ChatGPT
A single-use download link for a finished subtitle job: kind srt, vtt, ass, or burned (the captioned MP4, where the plan includes it).

get_transcription

ChatGPT
Fetch a single transcription (status, language, full transcript text) by its UUID so you can answer questions about it.

get_transcription_media_download

ChatGPT
A single-use link to the audio or video file behind one of the user's transcriptions.

get_usage_quota

ChatGPT
Read the current user's Shorty plan (Free / Premium / Pro), tier limits (upload sizes, realtime minutes, conversion caps), and current cloud-conversion usage against the daily quota.

list_granted_scopes

ChatGPT
The permissions this connection holds right now: scopes, the tiers they belong to, and how it authenticated (oauth or api key).

list_recent_articles

ChatGPT
List the current user's most recently summarized articles. Use when the user asks about their recent summaries, library overview, or 'what have I saved lately'.

list_transcriptions

ChatGPT
List the current user's audio/video transcriptions (newest first) with status and progress. Optional free-text query matches the transcript text.

request_scopes

ChatGPT
Ask the user — never choose for them. Which extra permission tiers the user will allow. Returns a single-use link; when the user opens it the app is reconnected and its next request asks for permissions again, with every tier selectable. API keys cannot be widened: create a new key instead.

search_articles

ChatGPT
Search the current user's Shorty library by free-text query (title, description, URL). Returns matching article cards with id, title, description, articleType and createdAt — pass the id to get_article for the full summary.

search_docs

ChatGPT
Search Shorty's developer documentation (API reference, error codes, webhooks, MCP guide) by free-text query. Returns matching pages with a snippet, the page URL, and a raw-Markdown twin URL you can fetch directly.

search_tools

ChatGPT
Find the Shorty MCP tools this connection can reach, returned as TypeScript declarations to call from execute_typescript. See the server instructions for the full contract.

create_content_summary

Claude

create_subtitles

Claude

create_transcription

Claude

create_youtube_summary

Claude

execute_typescript

Claude

get_article

Claude

get_job_status

Claude

get_transcription

Claude

get_usage_quota

Claude

list_recent_articles

Claude

list_transcriptions

Claude

search_articles

Claude

search_docs

Claude

search_tools

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/shorty"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/shorty)