MCP integration
The Model Context Protocol lets your chat client call our MCP server directly. Once installed, you can ask Claude, ChatGPT, or Grok to fetch a YouTube transcript without leaving the conversation.
Endpoint
A single Streamable HTTP endpoint serves every chat client:
https://api.youtubevideotranscript.io/mcpAuthentication
Two auth methods, same endpoint. Which one you use depends on what your client supports. See the per-client install guide for the exact path.
- API key (
yvt_live_*): paste into clients that accept a custom Bearer header. Used by Claude Code, VS Code / JetBrains / Cursor extensions, the xAI Grok UIs, and OpenAI’s Responses API. - OAuth 2.1: for clients whose UI only accepts an OAuth connector. Used by Claude.ai web, Claude Desktop, and ChatGPT’s consumer Apps & Connectors. The chat client discovers our authorization server, opens a consent page on
api.youtubevideotranscript.io, and you click Allow. No client_id pasting; PKCE + Dynamic Client Registration are handled automatically.
Tools exposed
| Tool | What it does | Cost |
|---|---|---|
get_transcript | Fetch the transcript for a single YouTube video. Accepts a full URL or an 11-character video ID. Optional language code. Optional format parameter (see below) controls the output shape. | 1 transcript credit on success |
list_channel_videos | Page through every video on a channel. Returns 30 per page with a continuation token. | Free |
list_playlist_videos | Same as channel listing but for playlists. | Free |
Transcript output formats
get_transcript accepts an optional format parameter so the model can pick the shape that matches what the user actually asked for. Token cost varies a lot.
format | Output | When to use |
|---|---|---|
text (default) | Plain prose, all segments joined, no timestamps. | Summaries, Q&A about content, theme extraction, sentiment, fact-checking. Cheapest token cost. |
timestamps | One segment per line as [mm:ss] text (auto[hh:mm:ss] for videos over an hour). | Citation, identifying clips for highlights or memes, suggesting cut points, building chapter lists, any task anchored to time positions. |
json | Full structured JSON with metadata, language, and per-segment objects. | Raw transcript data, programmatic post-processing, anything that needs every field. |
The MCP structuredContent response field is populated only when format="json". For text and timestamps, only the plain text block is sent, so MCP clients that surface structured content to the model don’t accidentally pull in the full JSON.
Per-client install guides
Each guide walks the exact UI clicks, copy-paste config, and a “try it” prompt to verify the connection.
- Claude: covers Claude.ai web, Claude Desktop, Claude Code CLI, and the VS Code / JetBrains / Cursor extensions.
- ChatGPT: covers ChatGPT.com with Developer Mode, Mac / Windows desktop apps, and the OpenAI Responses API for developers.
- Grok: covers grok.com/connectors and the xAI API. Availability depends on whether your Grok account exposes the Connectors menu.
Costs and rate limits
Same plan, same credits as the web app. A transcript fetched through MCP charges the same single transcript credit as a transcript fetched through the website. The per-plan rate limit from /api/v1 also covers /mcp, bucketed per user so multiple chat clients on the same account share one budget.
Free tier users get the same 10-transcript one-time grant inside MCP. Install the connector, try it, see if it’s worth upgrading.
Errors
Tool calls that fail return a structured MCP tool error to the chat client. The most common cases:
- Insufficient credits: your plan budget is exhausted for the current billing period.
- Wrong URL type: passing a channel URL to
get_transcriptreturns an error directing you tolist_channel_videosfirst. - Transcript unavailable: the video has no captions or upstream YouTube is degraded. No credit charged.