MCP Integration

Connect Claude, ChatGPT, Cursor, and OpenAI Agent Builder to SubDownload via Model Context Protocol.

Overview

Model Context Protocol (MCP) is a standardized framework that lets AI assistants call external tools directly. SubDownload's MCP server exposes 12 tools — including async AI transcription and a per-user Library — and supports OAuth 2.1 with Dynamic Client Registration (DCR) as well as static API keys.

Server Configuration

PropertyValue
Server URLhttps://api.subdownload.com/mcp
Auth metadata/.well-known/oauth-authorization-server
Dynamic registrationPOST /oauth/register
AuthorizeGET /oauth/authorize
TokenPOST /oauth/token
Scopemcp:access
Token prefixoat_ (OAuth) or sk_live_ (API key)

Client Setup

See the step-by-step guides:

MCP Tools

ToolCostPurpose
fetch_transcript1 creditFetch transcript by video URL/ID (params: video_url, lang).
search_youtube1 creditSearch videos or channels (params: query, type, limit).
resolve_channelfreeResolve @handle / URL / UC… ID to channel info (param: input).
search_channel_videos1 creditSearch videos within a channel (params: channel, query, limit).
get_channel_latest_videosfreeMost recent ~15 videos via RSS (param: channel).
list_channel_videos1 credit/pagePaginated uploads (params: channel or continuation).
list_playlist_videos1 credit/pagePaginated playlist (params: playlist or continuation).
transcribe_video5 credits on doneStart async AI Whisper transcription for videos without captions. Returns task_id + next_poll_after_seconds (params: video_url, lang).
get_asr_taskfreePoll an ASR task; returns segments when status=done (param: task_id).
list_libraryfreeList the user's saved transcripts and summaries (params: favorite, q, limit, offset).
get_library_itemfreeRead a saved item with transcript and summary inlined (params: id, locale).
save_to_library1 token-quota unitkind=asr flags a saved transcript; kind=summary uploads the AI's generated summary (params: video_id, kind, text, locale, model, …).

Error Handling

Failed tool calls never consume credits. Errors return user-friendly messages AI assistants can interpret naturally. See Error Codes for the full list.