get_youtube_transcriptLABSCO SUMMARY
Six tools instead of one, and the monitoring tool is free.
The reason to prefer this over a local transcript scraper is that research questions usually need discovery before extraction — find the videos, then read them — and both halves live behind one endpoint with one key. get_channel_latest_videos is free because it reads RSS, which makes daily upload monitoring viable as a habit rather than a budget line.
What it is
A hosted YouTube toolkit at transcriptapi.com. Most YouTube servers fetch one transcript; this one adds search, in-channel search, full channel listing, playlist extraction and RSS-based upload tracking, all remote so there is nothing to install locally.
What you get
get_youtube_transcriptreturns a transcript as markdown with metadata or as JSON, withinclude_timestampandsend_metadataboth defaulting to truesearch_youtubesearches videos or channels with a continuation token for paging, about 20 results per pageget_channel_latest_videosreturns roughly the 15 most recent uploads for a handle, URL or channel id — free, no credits chargedsearch_channel_videossearches inside one channel, about 30 results per pagelist_channel_videoslists a channel's whole library, about 100 per pagelist_playlist_videosreturns every video in a playlist, about 100 per page- One credit equals one successful request; failed and rate-limited calls do not consume credits
Requirements
A TranscriptAPI account — the free tier gives 100 credits at 60 requests per minute. Authenticate either with an API key beginning sk_, sent as a bearer token, or over OAuth 2.1: Claude Desktop, Claude Web and ChatGPT can register dynamically, so adding the URL is the whole setup. The endpoint is https://transcriptapi.com/mcp over Streamable HTTP; Claude Code registers it with claude mcp add --transport http. The repository is also an Agent Plugins 1.0.0 package containing no credentials, bundling the MCP server plus a skill that teaches an agent when to use each tool.
Setup effort
One command, then sign in — claude mcp add --transport http transcript-api https://transcriptapi.com/mcp, then approve the OAuth sign-in
USE CASES
01
Summarising a video someone sent you
Paste the URL and get the timestamped transcript pulled and condensed.
02
Researching a topic across creators
Search for the best videos, then read the transcripts of the top few.
03
Watching a channel without watching it
List new uploads each morning at no credit cost and decide what is worth your time.
04
Working through a course
Pull every video in the playlist, then transcribe them in order.
05
Finding one topic inside a huge channel
Search within that channel instead of scrolling its uploads.
6 tools
Listed in project docs. Your client may show a different list.
search_youtubeget_channel_latest_videossearch_channel_videoslist_channel_videoslist_playlist_videosBEFORE YOU INSTALL
What to know first
Tools you get
6 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
INSTALLATION
Connect your client
Server setup
claude mcp add
Claude Code
TERMINAL
claude mcp add --transport http transcript-api https://transcriptapi.com/mcpHosted endpoint
ENDPOINT URL
https://transcriptapi.com/mcpAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
MCP Clients
Claude.ai
Name: TranscriptAPI
URL: https://transcriptapi.com/mcp
How: Settings → Connectors → Add custom connector → Connect (browser authorization)
Cursor
CURSOR · JSON
{
"mcpServers": {
"transcript-api": {
"url": "https://transcriptapi.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}ChatGPT
MCP Server URL: https://transcriptapi.com/mcp
Client ID & Secret: optional — leave blank for Dynamic Client Registration
VS Code
VS CODE · JSON
{
"servers": {
"transcript-api": {
"type": "http",
"url": "https://transcriptapi.com/mcp"
}
}
}
