MCP server for fetching YouTube video transcripts
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"tubescribe-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# tubescribe-mcp MCP server for fetching [YouTube](https://www.youtube.com/) video transcripts. Thin wrapper around [`youtube-transcript-api`](https://pypi.org/project/youtube-transcript-api/). No API key required. ## Install ```bash pip install tubescribe-mcp ``` ## Usage ```bash tubescribe-mcp ``` The server runs on stdio transport (MCP standard). ## Tools **`get_transcript(video, languages?, timestamps?)`** — fetch a video transcript as plain text. - `video` — YouTube URL or bare 11-char video ID - `languages` — comma-separated preference codes, e.g. `"en,de"` (default: English) - `timestamps` — prefix each line with `[MM:SS]` (default: false) **`list_transcript_languages(video)`** — list available transcript languages for a video. ## Library ```python from tubescribe_mcp.transcript import fetch_transcript, list_languages, extract_video_id text = fetch_transcript("https://www.youtube.com/watch?v=dQw4w9WgXcQ") langs = list_languages("dQw4w9WgXcQ") vid = extract_video_id("https://youtu.be/dQw4w9WgXcQ") ``` ## License GPL-3.0-or-later
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.