BulkTranscripts: YouTube Transcripts のリモート MCP サーバーとは何ですか?
BulkTranscripts: YouTube Transcripts のリモート MCP サーバーは、https://bulktranscripts.co/mcp にホストされた Model Context Protocol エンドポイントです。AI アシスタントはローカルに何もインストール・実行することなく接続できます。
BulkTranscripts: YouTube Transcripts MCP Server認証済み注目
基本情報
BulkTranscripts: YouTube Transcripts MCP Server について
Transcripts for one YouTube video or a whole channel or playlist, plus YouTube search, channel and playlist listings, and free new-upload tracking.
接続情報
https://bulktranscripts.co/mcpセットアップ
claude mcp add bulktranscripts-youtube-transcripts --transport http https://bulktranscripts.co/mcpBulkTranscripts: YouTube Transcripts MCP Server のツール
10Fetch the full transcript of one YouTube video as clean text with metadata (title, channel, duration, upload date, language). Accepts a watch URL, youtu.be link, Shorts URL, or bare 11-character video id. Costs 1 credit the first time it is added to this account's library; repeat reads are free. Set include_segments to true only when per-line timestamps are needed (much larger output).
Fetch transcripts for up to 20 videos in one call — pass an array of YouTube URLs or ids. Videos are fetched in parallel and the call returns within about 40 seconds; any video still being fetched at that point is listed in `failed` with code still_fetching, is not charged, and keeps fetching in the background — call this tool again with those ids in 15-30 seconds and they return instantly. Each new library addition costs 1 credit; repeats from this account's library are free. Videos without captions are reported per-item and do not fail the batch. For whole channels or playlists, first list the videos with get_channel_videos / get_playlist_videos, then batch the ids through this tool; one call counts as one request against the rate limit however many videos it holds. If the balance runs out, completed items are returned with partial=true and an out_of_credits stopped block.
Search YouTube by keyword for videos, channels, or playlists (set type). Returns titles, ids, and URLs — useful for research, discovery, and finding videos to transcribe. Costs 1 credit per search.
Search within one channel's uploads to find its videos on a topic — great for researching what a creator has said about something without listing the whole archive. Accepts @handle, channel URL, or UC… id. Costs 1 credit.
List the videos of a YouTube channel (id, title, duration, URL) without fetching transcripts. Accepts @handle, channel URL, or UC… channel id. Costs 1 credit. Chain into get_transcripts to bulk-extract.
List every video in a YouTube playlist, in playlist order (courses and series keep their sequence). Accepts a playlist URL or bare playlist id (13, 18, 26 or 34 characters — all valid). Public and unlisted playlists only: YouTube reports a private playlist as nonexistent (error playlist_private) — ask the owner to set Visibility to Unlisted. Costs 1 credit. Chain into get_transcripts to bulk-extract.
Get a channel's newest uploads (up to 15) with publish dates, from YouTube's RSS feed (or a lightweight listing when the feed is unavailable). Always free — no credit charged — so it is ideal for monitoring channels, daily recaps, and 'did they post this week?' checks. Accepts @handle, URL, or UC… id.
Extract every transcript of a YouTube channel, playlist or video list in the background. Returns immediately with a run_id; the server discovers the videos (free), fetches each transcript into this account's library (1 credit per new transcript, cache hits and repeats free, failures never charged) and keeps going after this call returns. Poll get_bulk_status no sooner than its check_again_in_seconds, then page outcomes with list_bulk_results and read any transcript with get_transcript (free once it is in the library). Up to 1,000 videos per job, 2 jobs per account at a time. Prefer this over repeated get_transcripts calls for anything larger than about 20 videos.
Progress of a job started with start_bulk_extract: status (running, completed, stopped, failed), total, completed, failed, skipped (no captions), quota (not attempted for lack of credits), remaining, and check_again_in_seconds. Free. Wait at least check_again_in_seconds between polls; 0 means the job is finished.
One page of per-video outcomes for a bulk job: video id, title, channel, duration, word count and status (ok, cached, or error with a code). Never includes transcript text; fetch any listed video with get_transcript, which is free once the job has put it in the library. Pass next_cursor from the previous page to continue. Free.
概要
What is BulkTranscripts?
BulkTranscripts is a hosted MCP server that gives AI agents clean YouTube transcripts without running yt-dlp locally or fighting IP blocks. Point it at one video, a whole channel or a playlist and it returns clean text with metadata, with timestamped segments on request.
Tools
| Tool | What it does |
|---|---|
get_transcript | Transcript of one YouTube video |
get_transcripts | Up to 20 transcripts in one call |
get_channel_videos / get_playlist_videos | List every video in a channel or playlist |
start_bulk_extract / get_bulk_status / list_bulk_results | Background extraction for a whole channel or playlist (up to 1,000 videos) |
search_youtube | Search YouTube for videos, channels or playlists |
search_channel | Search inside one channel |
get_latest_videos | A channel's newest uploads, free and never charged |
No tool deletes or overwrites anything; the transcript tools add what they fetch to your library.
How to connect
Add https://bulktranscripts.co/mcp as a remote (streamable HTTP) MCP server in Claude, ChatGPT, Cursor, VS Code or any MCP client. Sign in with Google over OAuth for 30 free credits, or send an API key as a Bearer token. Setup guide: YouTube MCP server.
Pricing
One credit per new transcript. Transcripts already in your library are free to re-read forever, and checking a channel for new uploads is free. Credit packs: bulktranscripts.co.
Links
- Website: https://bulktranscripts.co
- MCP setup: https://bulktranscripts.co/youtube-mcp-server
- REST API docs: https://bulktranscripts.co/docs
- GitHub: https://github.com/pratie/bulktranscripts-mcp
よくある質問
BulkTranscripts: YouTube Transcripts の MCP サーバーにはどう接続しますか?
エンドポイント https://bulktranscripts.co/mcp を Claude Code、Cursor、VS Code など任意の MCP 対応クライアントに追加してください。このページのセットアップ手順で各クライアントを一度に設定できます。
BulkTranscripts: YouTube Transcripts の MCP サーバーは認証が必要ですか?
はい。BulkTranscripts: YouTube Transcripts は OAuth を使用します。初回接続時に MCP クライアントがブラウザを開いてサインイン・認可を行い、以降はその認証情報を再利用します。
BulkTranscripts: YouTube Transcripts の MCP サーバーはどのトランスポートを使用しますか?
BulkTranscripts: YouTube Transcripts は Streamable HTTP エンドポイントを公開しており、これはリモート MCP サーバーで広く使われ、主要な MCP クライアントがサポートするトランスポートです。
他のリモート MCP サーバー
A
Aayat AI
Pay-per-use data and tools for AI agents: crypto token safety and rug checks, web search with cited answers, page-to-Markdown, up-to-date library docs, package safety, company research and UK/EU open data. 160 tools, 20
A
ASO Atlas
App Store keyword research, rank tracking, competitor analysis and authorized performance data.
Adgentek Ad Server (AdsMCP)
AdsMCP is the MCP entry point into the Adgentek Ad Server. Call ads_serve with the conversation context and get back a native ad matched to user intent, or no ad when one does not fit. Publishers earn on a CPM basis. Fre
AOI — Environmental Intelligence
AOI is a commercial environmental-intelligence gateway that gives AI agents programmatic access to 38 real-world intelligence capabilities — climate risk, satellite monitoring, methane detection, water & soil, vegetation
A
AI-Ready Webpage Extractor (Apify)
Convert web pages to clean Markdown and retrieval-ready chunks with browser rendering support.
コメント