SubDownload
OfficialSubDownload is an MCP server that exposes YouTube as a data source, enabling AI agents to search, retrieve, transcribe, and manage YouTube content with a personal knowledge base.
Search YouTube: Perform keyword searches across all of YouTube
Fetch Video Metadata: Retrieve video details including title, channel, duration, view count, and publish date
Fetch Transcripts: Get full transcripts with timestamps for YouTube videos, supporting multiple languages
AI Transcription: Generate transcripts for videos lacking captions using AI-powered ASR, with a polling mechanism to check job status
Channel Management: Resolve channels by handle/URL/ID, list all channel videos (with pagination), get latest videos, and search within a specific channel
Playlist Management: List all videos contained within a YouTube playlist
Personal Knowledge Base: Save video summaries or transcripts with optional tags, browse saved items by search query or tags, and retrieve specific items by ID
Provides tools for searching YouTube, fetching video metadata and transcripts (including AI ASR for videos without captions), managing channels and playlists, and saving content to a personal knowledge base.
SubDownload MCP Server
SubDownload exposes YouTube as an MCP-native data source. Connect once via OAuth and your AI agent gets tools to summarize videos, fetch full transcripts (including videos without captions, via AI ASR), search channels and playlists, and save everything into a per-user knowledge base for cross-session recall.
Hosted endpoint:
https://api.subdownload.com/mcpHomepage: https://subdownload.com?utm_source=gthb_awesome_9jqqed&utm_medium=code&utm_campaign=Awesome
Glama (connector): https://glama.ai/mcp/connectors/com.subdownload.api/sub-download
Glama (server): https://glama.ai/mcp/servers/SubDownload/subdownload-mcp
The recommended setup is to point your MCP client directly at the hosted endpoint above and authenticate via OAuth — see "Quick connect" below. This repo also ships a thin stdio proxy (Node + Docker) for environments that prefer a local subprocess.
Auth
OAuth 2.1 with Dynamic Client Registration (RFC 7591). No pre-shared client_id or client_secret — your MCP client registers itself on first connect.
Discovery (RFC 9728):
POST to
/mcpwithout a token returns401plus aWWW-Authenticateheader pointing to/.well-known/oauth-protected-resourceThat document points to the authorization server (
https://api.subdownload.com)The MCP client follows the standard authorize → callback → token flow with PKCE
API-key alternative: every account at https://subdownload.com/account exposes a Bearer token for clients that don't support OAuth.
Related MCP server: YouTube Transcript MCP Server
Tools
Tool | What it does |
| Keyword search across YouTube |
| Video metadata (title, channel, duration, view count) |
| Full transcript with timestamps |
| Generate a transcript with AI ASR for videos that have no captions |
| Poll an in-progress AI transcription job |
| Look up a channel by handle, URL, or ID |
| List videos on a channel |
| Latest videos for a channel |
| Search within a single channel |
| List the contents of a playlist |
| Save a video summary or transcript to your personal knowledge base |
| Browse your saved knowledge base |
| Fetch a single saved item |
Quick connect
Claude Desktop / Cursor / Windsurf / any OAuth-capable MCP client
{
"mcpServers": {
"subdownload": {
"url": "https://api.subdownload.com/mcp"
}
}
}The first time you use it, the client triggers OAuth and you sign in with Google or LINUX DO. Free credits on signup — no card required.
Bearer-token clients
{
"mcpServers": {
"subdownload": {
"url": "https://api.subdownload.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Grab your API key from your account page.
Local stdio proxy (Docker / npm)
For clients that prefer a subprocess transport, this repo ships a thin Node proxy that forwards tools/call to the hosted endpoint with your API key.
# Docker
docker build -t subdownload-mcp .
docker run --rm -i -e SUBDOWNLOAD_API_KEY=YOUR_API_KEY subdownload-mcp
# Or via Node directly
npm install
SUBDOWNLOAD_API_KEY=YOUR_API_KEY npm startClient config example:
{
"mcpServers": {
"subdownload": {
"command": "docker",
"args": ["run", "--rm", "-i", "-e", "SUBDOWNLOAD_API_KEY", "subdownload-mcp"],
"env": { "SUBDOWNLOAD_API_KEY": "YOUR_API_KEY" }
}
}
}Tool schemas are declared inline so introspection (initialize, tools/list) works without credentials; tools/call requires SUBDOWNLOAD_API_KEY.
Pricing
Free credits on signup. Pro: 5,000 credits per month. See https://subdownload.com/pricing.
Support
Email: contact@subdownload.com
Status: https://subdownload.com/status
License
MIT (applies to this documentation repository; the SubDownload service itself is hosted SaaS — see https://subdownload.com/terms).
Available Tools
13 toolsfetch_transcriptARead-only
Fetch the existing official transcript (subtitles/captions) of a YouTube video, with per-segment timestamps and language detected. Errors with NO_CAPTIONS if the video has no captions — fall back to transcribe_video in that case to generate one with AI ASR. This call is free.
Inputs: video_id (required), lang, save.
fetch_video_infoARead-only
Fetch consolidated YouTube video metadata with numeric types — title, channel, duration, view count, publish date, thumbnail, description, captions availability. Does NOT include the transcript itself; call fetch_transcript or transcribe_video for that. Cheap, fast, free.
Inputs: video_id (required).
get_asr_taskARead-only
Poll the status of an ASR task created by transcribe_video. Returns one of queued, downloading, transcribing, finalizing, done, or failed. When status is done, includes the full transcript with timestamps. Recommended polling interval: 3-5 seconds. Free — does not consume credits.
Inputs: task_id (required).
get_channel_latest_videosARead-only
Get the most recent videos from a YouTube channel — convenience wrapper over list_channel_videos with no pagination. Best for 'what did this creator publish recently?' style queries.
Inputs: channel (required).
get_library_itemARead-only
Read a saved Library item with its transcript and AI summary inline (when available). Use after list_library to fetch the full content the user saved. Free.
Inputs: id (required), locale.
list_channel_videosARead-only
List all videos from a YouTube channel ordered by publish date (newest first), with pagination. Returns up to 30 per page plus a continuation token if more results exist. For just the most recent handful, prefer get_channel_latest_videos for simplicity.
Inputs: channel, continuation.
list_libraryARead-only
List videos the user has saved to their Library (transcripts + summaries). Supports substring search on title/author, favorites filter, and pagination. Returns recently saved items first. Scoped to the calling user's data only.
Inputs: favorite, q, limit, offset.
list_playlist_videosARead-only
List videos in a YouTube playlist in order, with pagination. Returns video metadata and position within the playlist. Works for any public or unlisted playlist exposed by its URL/ID.
Inputs: playlist, continuation.
resolve_channelARead-only
Resolve a YouTube @handle, channel URL, video URL, or raw channel ID into canonical channel info (channel ID, name, handle, subscriber count, video count, avatar). Call this first when you only have a handle or URL but need a channel ID for the other channel-scoped tools.
Inputs: input (required).
save_to_libraryAIdempotent
Save a video to the authenticated user's Library. Three modes via kind: 'asr' bookmarks the video and flips has_asr (use after a successful transcribe_video → fetch_transcript flow); 'summary' uploads a summary blob; 'both' does both at once. Idempotent: saving the same video twice updates the existing entry.
Inputs: video_id (required), kind (required), title, author, +7 more.
search_channel_videosARead-only
Search for specific videos within a single YouTube channel. Restricts results to the given channel. Use after resolve_channel if starting from a handle. Useful for 'find Karpathy's video about backpropagation' style queries.
Inputs: channel (required), q (required), limit.
search_youtubeARead-only
Search YouTube globally for videos, channels, or playlists on any topic. Returns up to 50 results with metadata. Use this for topic-based discovery when the user has not specified a channel — for searching within a known channel use search_channel_videos instead.
Inputs: q (required), type, limit.
transcribe_videoAIdempotent
Start an asynchronous AI ASR (Whisper) transcription of a YouTube video. Returns immediately with a task_id and estimated_wait_seconds; the actual transcription runs in the background. Poll status with get_asr_task. Use this when fetch_transcript returned NO_CAPTIONS or when the video has no captions. Costs 5 credits, debited only on successful completion.
Inputs: video_url (required), lang.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Most tools have clearly distinct purposes, but fetch_transcript vs transcribe_video and list_channel_videos vs get_channel_latest_videos overlap enough that users could initially pick the wrong one. The descriptions provide good disambiguation, so only a slight deduction.
All tools follow a consistent verb_noun snake_case pattern: list_, get_, fetch_, search_, transcribe_, resolve_, save_. Minor variation between 'fetch' and 'get' is semantically negligible and does not break the pattern.
13 tools is well within the ideal range for this domain, covering channel discovery, video search, transcript fetch/generation, ASR status polling, and library management without unnecessary bloat.
The toolset covers the main workflows of finding videos, fetching or generating transcripts, and saving/reading library items. Obvious gaps are the lack of a library delete/update tool and no way to list available caption tracks before requesting a transcript.
Maintenance
Related MCP Connectors
SubDownload exposes YouTube as an MCP-native data source. Connect via OAuth and your AI agent can summarize videos, fetch full transcripts (even for videos with no captions, via AI ASR), search across channels, and save everything into a private knowledge base. Works with Claude, ChatGPT, Cursor, and 40+ MCP clients. Free credits on signup, no card required.
An MCP server that gives any LLM or agent clean YouTube transcripts on demand: a single video, a whole channel, or a playlist, plus AI cleanup of auto-generated captions. API-key auth, credit-based, same backend as the public v1 API. Get a free API key with 25 free credits at youtubetranscriptdownload.com/account.
YouTube Transcript, Subtitles & Comments MCP. Zero-signup x402 USDC ($0.001) on Base or API key.
YouTube Transcript, Subtitles & Comments MCP. Zero-signup x402 USDC ($0.001) on Base or API key.
Related MCP Servers
- AlicenseBqualityFmaintenanceA server that leverages Playwright for automated browser testing and integrates with Cloudflare Workers, enabling AI assistants to control web browsers for navigation, interaction, and screenshots.22261Apache 2.0
- AlicenseAqualityDmaintenanceEnables users to extract, search, and analyze YouTube video transcripts directly within MCP-compatible clients. It supports advanced features like time-chunked summaries, keyword searching with surrounding context, and batch processing for multiple videos.4MIT
- AlicenseAqualityCmaintenanceMCP server that fetches YouTube video transcripts and optionally summarizes them. Supports multiple transcript formats (text, JSON, SRT, WebVTT), multi-language retrieval, and flexible YouTube URL parsing.649 PyPI6MIT
- FlicenseNot gradedqualityDmaintenanceMCP server providing tools to fetch YouTube video transcripts with metadata, supporting direct YouTube transcripts and audio transcription via multiple backends (whisper, AssemblyAI, OpenAI, Gemini).-