YouTube Transcript MCP: read and search video transcripts

How to connect YouTube Transcript to Claude, ChatGPT or Cursor

1. 1Click Connect YouTube Transcript free and paste an API key from your YouTube Transcript account.
2. 2Every tool is on once you connect. Fetching new captions uses credits, and a batch multiplies that by up to 10 videos, so switch off batch fetches if your AI app should mostly read transcripts you've already stored.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app to fetch the transcript of a conference talk and list its key points, then open Activity to see the call.

What your AI app can do with YouTube transcripts

• Fetch captions for one YouTube video, or for 1 to 10 at once, and store them in your account.
• Read and search transcripts you've already stored without using more credits.
• Turn a playlist or channel into a list of videos before deciding what to transcribe; this needs a Basic plan or higher.
• List a transcript's stored languages and the languages it can be translated into.
• Search what people say across 425k videos with YouTube Transcript's own server.

Keep transcript credits in check

• Switch off batch fetches and channel or playlist lookups, and your AI app can still fetch one video at a time.
• Activity records every transcript call, so credit use can be traced to the request behind it.

What you get with YouTube Transcript and ContextGate

• Your AI apps can use YouTube TranscriptClaude, Cursor, ChatGPT and other AI apps reach YouTube Transcript through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any YouTube Transcript tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

YouTube Transcript tools

Examples of what your AI apps can do in YouTube Transcript. You'll see the exact list of tools after you connect it.

• Get Stored TranscriptRead a transcript already stored in the connected account without submitting new transcription work or consuming retrieval credits.
• Get Video TranscriptFetch captions for one YouTube video and store the resulting transcript in the connected account. This consumes provider credits, but never starts ASR. The tool waits up to 20 seconds for asynchronous
• Get Video Transcript Job StatusRead one transcript job's current processing, completed, failed, or requires-ASR-confirmation state without creating work or waiting. Use this one-shot read when GET_VIDEO_TRANSCRIPT times out, passin
• Get Video Transcripts BatchFetch and store captions for 1-10 YouTube videos. Each uncached video can consume provider credits, so cost scales with the request size. ASR never starts. This creates one batch and waits up to 20 se
• Get Video Transcripts Batch StatusRead the current state and available per-video results for a transcript batch without creating work or waiting. Use this one-shot read to recover when GET_VIDEO_TRANSCRIPTS_BATCH times out while the p
• List Stored TranscriptsList and search transcripts already stored in the connected account, one bounded page at a time.
• List Transcript LanguagesList stored languages and YouTube translation target languages for one owned video transcript.
• Resolve Channel VideosRequires Basic or higher. Resolve a YouTube channel into bounded upload metadata without transcribing the videos. This may count against the account's monthly channel allowance.
• Resolve Playlist VideosRequires Basic or higher. Resolve a YouTube playlist into bounded video metadata without transcribing the videos. This may count against the account's monthly playlist allowance.