YouTube Transcript Downloader
Clean YouTube transcripts for agents: single videos, channels, playlists, plus AI caption cleanup.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"transcripts": {
"url": "https://youtubetranscriptdownload.com/api/mcp"
}
}
}遠端端點
https://youtubetranscriptdownload.com/api/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢get_transcript(video)
Get the full transcript of a single YouTube video as timestamped markdown. Read-only: fetches existing captions, modifies nothing. Requires an API key; each successful call charges 1 credit, including repeat calls for the same video, so reuse a transcript already in context instead of re-fetching. Videos without captions return an error and cost nothing. Rate limit: 5 requests per 10 seconds.
輸入結構描述
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "YouTube video ID (e.g. dQw4w9WgXcQ) or full video URL (youtube.com/watch?v=... or youtu.be/... forms)"
}
},
"required": [
"video"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"videoId": {
"type": "string",
"description": "YouTube video ID"
},
"title": {
"type": "string",
"description": "Video title"
},
"transcript": {
"type": "string",
"description": "Full transcript as timestamped markdown"
},
"creditsUsed": {
"type": "number",
"description": "Credits charged for this call"
},
"creditsRemaining": {
"type": "number",
"description": "Account balance after this call"
}
},
"required": [
"videoId",
"title",
"transcript",
"creditsUsed",
"creditsRemaining"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢polish_transcript(video)
Get a cleaned-up transcript of a YouTube video's auto-generated captions: punctuation and capitalisation restored, filler and false starts removed, paragraphs added, misheard names fixed, faithful to what was said. Use when raw captions are too messy to read or quote; for a plain transcript use get_transcript. Read-only; requires an API key. Each call charges credits by transcript length (about 3 per 1,000 words, minimum 5), including repeat calls, so keep the result in context. Human-uploaded captions (already clean) and transcripts over ~7,000 words return an error without charging. Rate limit: 5 requests per 10 seconds.
輸入結構描述
{
"type": "object",
"properties": {
"video": {
"type": "string",
"description": "YouTube video ID (e.g. dQw4w9WgXcQ) or full video URL (youtube.com/watch?v=... or youtu.be/... forms)"
}
},
"required": [
"video"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"videoId": {
"type": "string",
"description": "YouTube video ID"
},
"title": {
"type": "string",
"description": "Video title"
},
"transcript": {
"type": "string",
"description": "Cleaned transcript as timestamped markdown"
},
"creditsUsed": {
"type": "number",
"description": "Credits charged for this call (scales by length)"
},
"creditsRemaining": {
"type": "number",
"description": "Account balance after this call"
}
},
"required": [
"videoId",
"title",
"transcript",
"creditsUsed",
"creditsRemaining"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢get_channel_transcripts(url, limit)
Get transcripts for a YouTube channel's most recent videos (newest first) as timestamped markdown, one section per video. Use for research across a creator's recent output; for one known video use get_transcript. Read-only; requires an API key. Charges 1 credit per video that returns a transcript, including repeat calls; videos without captions are skipped free. A 10-video call typically costs up to 10 credits, so start with a small limit. Rate limit: 5 requests per 10 seconds.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "YouTube channel URL or handle (e.g. https://www.youtube.com/@lexfridman or @lexfridman)"
},
"limit": {
"default": 10,
"description": "Number of most-recent videos to fetch, 1-50 (default 10). Upper bound on the credit charge for this call.",
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"channel": {
"type": "string",
"description": "Channel name"
},
"totalVideos": {
"type": "number",
"description": "Videos attempted in this call"
},
"succeeded": {
"type": "number",
"description": "Videos that returned a transcript (each charged 1 credit)"
},
"failed": {
"type": "number",
"description": "Videos skipped without charge (no captions)"
},
"transcripts": {
"type": "string",
"description": "All transcripts as timestamped markdown, one section per video, divider-separated"
},
"creditsUsed": {
"type": "number",
"description": "Credits charged for this call"
},
"creditsRemaining": {
"type": "number",
"description": "Account balance after this call"
}
},
"required": [
"channel",
"totalVideos",
"succeeded",
"failed",
"transcripts",
"creditsUsed",
"creditsRemaining"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢get_playlist_transcripts(url, limit)
Get transcripts for the videos in a YouTube playlist (in playlist order) as timestamped markdown, one section per video. Use for working through a course, series, or curated list; for one known video use get_transcript. Read-only; requires an API key. Charges 1 credit per video that returns a transcript, including repeat calls; videos without captions are skipped free. A 10-video call typically costs up to 10 credits, so start with a small limit. Rate limit: 5 requests per 10 seconds.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "YouTube playlist URL (e.g. https://www.youtube.com/playlist?list=PLxxxxxx)"
},
"limit": {
"default": 10,
"description": "Number of videos to fetch from the start of the playlist, 1-50 (default 10). Upper bound on the credit charge for this call.",
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"playlist": {
"type": "string",
"description": "Playlist title"
},
"totalVideos": {
"type": "number",
"description": "Videos attempted in this call"
},
"succeeded": {
"type": "number",
"description": "Videos that returned a transcript (each charged 1 credit)"
},
"failed": {
"type": "number",
"description": "Videos skipped without charge (no captions)"
},
"transcripts": {
"type": "string",
"description": "All transcripts as timestamped markdown, one section per video, divider-separated"
},
"creditsUsed": {
"type": "number",
"description": "Credits charged for this call"
},
"creditsRemaining": {
"type": "number",
"description": "Account balance after this call"
}
},
"required": [
"playlist",
"totalVideos",
"succeeded",
"failed",
"transcripts",
"creditsUsed",
"creditsRemaining"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}社群
證據