get_transcript
Extract transcript from YouTube video URL
LABSCO SUMMARY
One call, and nothing to discover.
get_transcript takes url and language and returns the transcript; there is no search tool, no metadata call, and no way to ask in advance which languages a given video actually carries. The workflow this fits is one where the video was already chosen somewhere else and the language is known — it will not help you find either. That narrowness is the whole design, and it is worth knowing before it is wired into a pipeline that assumes discovery.
What it is
A single-tool server that returns the transcript of a YouTube video from its URL.
What you get
- get_transcript takes the video url and a language, and returns the transcript text.
- That call is the whole surface: there is no video search and no separate listing of which languages a video carries, so language is the only choice being made at call time.
Requirements
A Cloudflare account to deploy your own copy of the Worker; the server itself asks for no key. get_transcript needs the URL of a video that carries a transcript, and the language to pull it in.
Setup effort
Build from source — git clone https://github.com/Mohammad1704/youtube-transcript-mcp.git
USE CASES
01
Reading what was said in a video you already have the link to
Pass the URL and the language you want it in, and work from the text instead of the video.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation. Language is a parameter (en, es, tr), defaulting to English; the Worker caches transcripts for seven days.
Requires
- Node.js and npm (to deploy with wrangler)
- A Cloudflare account
- npx on PATH (for mcp-remote)
CONTEXT COST
Light Standing cost
Rated by the size of the one tool definition that rides along on every turn
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
TERMINAL
git clone https://github.com/Mohammad1704/youtube-transcript-mcp.git
cd youtube-transcript-mcp
npm install
npx wrangler loginCreate your own KV namespace for the transcript cache — the repo's wrangler.toml points TRANSCRIPT_CACHE at the author's namespace id.
TERMINAL
npx wrangler kv namespace create TRANSCRIPT_CACHEIn wrangler.toml, set the id under [[kv_namespaces]] to the id that command printed, then deploy.
TERMINAL
npm run deployWrangler prints your workers.dev URL; clients connect to that URL with /sse on the end.
MCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"youtube-transcript": {
"command": "npx",
"args": [
"mcp-remote",
"https://youtube-transcript-mcp.<YOUR_SUBDOMAIN>.workers.dev/sse"
]
}
}
}Use the workers.dev URL that npm run deploy printed, with /sse on the end.
