YouTube Transcript MCP Server

Give Claude, ChatGPT, Cursor, Claude Code and any MCP client the ability to read YouTube transcripts. Hosted, nothing to install. Free API key: 10 requests a day.

A hosted Model Context Protocol server that exposes one tool, get_youtube_transcript, backed by youtube-transcript.ai. Paste a YouTube link mid-conversation and your AI reads the full transcript on demand.

Connector URL:

https://youtube-transcript.ai/mcp?key=YOUR_KEY

Replace YOUR_KEY with your API key. Create a free key with a Google sign-in; it takes about a minute.

Why

Free to start. A free key covers 10 transcripts a day. Pro is 1,000 a day for $120 a year, on the same key.
Reliable. A hardened fetch pipeline with proxy fallback returns transcripts even on videos that block typical scrapers.
Any language. Pick a caption track by language code (en, zh-CN, es, ja, …) or let it choose the default.
Built for agents. One tool, plain-text output with title and metadata. Multi-hour videos come back in parts, so nothing gets cut off.

Authentication

Tool calls need an API key. There is no OAuth. Send the key in one of two ways:

Where	Example
Header	`Authorization: Bearer YOUR_KEY`
URL	`https://youtube-transcript.ai/mcp?key=YOUR_KEY`

The URL form is for clients that only accept a connector URL.

Quick start

Claude (web / desktop)

Settings → Connectors → Add custom connector

Field	Value
Name	`youtube-transcript.ai`
URL	`https://youtube-transcript.ai/mcp?key=YOUR_KEY`

Then ask: “Summarize this video: https://youtu.be/dQw4w9WgXcQ”

ChatGPT

In the custom connector / MCP server setup, add an MCP server with URL https://youtube-transcript.ai/mcp?key=YOUR_KEY (transport: Streamable HTTP), enable it for your chat, then paste a YouTube link.

Claude Code

claude mcp add --transport http --scope user youtube-transcript \
  https://youtube-transcript.ai/mcp \
  --header "Authorization: Bearer YOUR_KEY"

Cursor

Add to ~/.cursor/mcp.json, or to .cursor/mcp.json inside one project:

{
  "mcpServers": {
    "youtube-transcript": {
      "url": "https://youtube-transcript.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_KEY" }
    }
  }
}

Codex

Add to ~/.codex/config.toml:

[mcp_servers.youtube-transcript]
url = "https://youtube-transcript.ai/mcp"
http_headers = { "Authorization" = "Bearer YOUR_KEY" }

Clients that only launch local servers

For clients that start MCP servers from a config file and cannot take a remote URL, bridge with mcp-remote:

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://youtube-transcript.ai/mcp?key=YOUR_KEY"]
    }
  }
}

Let your agent do it

Paste https://youtube-transcript.ai/mcp.md into a coding agent. It is a plain-text version of these instructions, written for an AI to follow.

Tool reference

`get_youtube_transcript`

Fetch the full text transcript of a YouTube video.

Parameter	Type	Required	Description
`video`	string	yes	YouTube URL (watch, `youtu.be`, shorts, embed) or a bare 11-character video ID
`lang`	string	no	Caption language code, e.g. `en`, `zh-CN`, `es`. Omit for the default track
`offset`	integer	no	Where to continue a long transcript. Use the value given at the end of the previous part

Returns plain text: the transcript with title, duration, and a list of available languages. Transcripts over 120,000 characters come back in parts; each part ends with a note giving the offset for the next call.

Example prompts

“Summarize the key points of <link> in 5 bullets.”
“Pull the transcript of this video and translate it to Spanish.”
“What does the speaker say about pricing in <link>? Quote the exact lines.”

Programmatic use

The server speaks standard MCP over Streamable HTTP (JSON-RPC). A zero-dependency example is in examples/quickstart.mjs:

YT_TRANSCRIPT_KEY=YOUR_KEY node examples/quickstart.mjs https://youtu.be/dQw4w9WgXcQ

Calling from your own code without MCP? There is a plain HTTP endpoint too: see the YouTube Transcript API.

Limits

Free: 10 requests a day. Pro: 1,000 a day for $120 a year. Upgrade from the key page.
Every tool call counts as one request, including each part of a long transcript. The count resets at 00:00 UTC.
The video needs captions, either written by the uploader or auto-generated by YouTube.

Notes

Not affiliated with YouTube or Google. Transcripts are fetched from publicly available captions.
Listed in the official MCP Registry as ai.youtube-transcript/youtube-transcript.

License

MIT

YouTube Transcript AI

PLUG IN

README