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:

http
https://api.youtubevideotranscript.io/mcp

Authentication

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

ToolWhat it doesCost
get_transcriptFetch 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_videosPage through every video on a channel. Returns 30 per page with a continuation token.Free
list_playlist_videosSame 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.

formatOutputWhen to use
text (default)Plain prose, all segments joined, no timestamps.Summaries, Q&A about content, theme extraction, sentiment, fact-checking. Cheapest token cost.
timestampsOne 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.
jsonFull 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_transcript returns an error directing you to list_channel_videos first.
  • Transcript unavailable: the video has no captions or upstream YouTube is degraded. No credit charged.

We use Google Analytics cookies and note which site referred you, so we know how people find us. Nothing personal, nothing sold. See our Privacy Policy.