io.github.bepolabs/youtube-transcripts
YouTube Transcript Scraper: video captions and subtitles
Is the YouTube Transcript Scraper MCP server down? No. It is up and needs auth (HTTP 401), probed 2026-11-14.
Feed links or IDs and receive spoken words with timings as JSON for summaries, LLMs and AI agents.
needs auth probed 2026-11-14 · HTTP 401 · Bearer
Streamable HTTP error: Error POSTing to endpoint: {"error":"invalid_token","error_description":"Missing or invalid access token. Pass an Apify API token in the - Endpoint
- https://mcp.apify.com?tools=bepolabs/youtube-transcripts (streamable-http)
- Host
- mcp.apify.com
- Getting access
- OAuth with dynamic client registration. A client such as Claude Code, Cursor or npx mcpcost auth https://mcp.apify.com?tools=bepolabs/youtube-transcripts registers itself and opens the consent page; the publisher has nothing to set up for you.
Authorization server console-backend.apify.com, PKCE S256, grants authorization_code, refresh_token, urn:ietf:params:oauth:grant-type:device_code.
Scopes full_api_access.
Read from the server's public OAuth metadata, without a token. Method. - Website
- https://apify.com/bepolabs/youtube-transcripts
- Registry
- active, updated 2026-11-12 · registry entry
Compare this server with others.
More servers
Other registry entries on mcp.apify.com, the ones next to this name; all of them.
- Website to Markdown Crawler: HTML to Markdown for LLM and RAG io.github.bepolabs/web-to-markdown · not probed
- Contact Details Scraper: email, phone and socials for outreach io.github.bepolabs/website-contacts · needs auth
- Website Screenshot Generator: full-page, mobile, PNG or PDF io.github.bepolabs/website-screenshot · needs auth
- Wikipedia Pageviews Scraper: page views for any topic or person io.github.bepolabs/wikipedia-pageviews · needs auth
- Domain Intelligence Check io.github.bkeller-research/domain-intel-check · needs auth
- Google Ads Transparency Center Scraper io.github.bkeller-research/google-ads-transparency-center · needs auth
- Google Play App Check io.github.bkeller-research/google-play-app-check · needs auth
- Hiring Signal Check io.github.bkeller-research/hiring-signal-check · needs auth
Servers that mention transcripts.
- ai.backengine/backengine-mcp · needs auth
- ai.bidclub/bidclub · alive
- Lenny Rachitsky Podcast Transcripts MCP Server ai.com.mcp/lenny-rachitsky-podcast · alive
- Contio MeetingOS ai.contio/meetingos · needs auth
- Distilla ai.distilla/mcp · needs auth
- Fireflies.ai ai.fireflies/fireflies · needs auth
- Gavelin ai.gavelin/mcp · needs auth
- Meeting.ai ai.meeting/memo-mcp · needs auth
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The server answers HTTP 401 to an unauthenticated initialize, so the probe cannot list its tools. That is correct for a private server. Some public servers answer initialize and tools/list without credentials and ask for auth on tool calls only; those get a token count here.
Fixed something? Probe it now, with the same steps as the daily run. This page updates with the next daily run.