YouTube Transcript + YouTube Search MCP
YouTube transcripts, search, channel browsing, and playlists for AI agents via MCP.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"youtube-transcript-and-youtube-search": {
"url": "https://getyoutubetranscript.com/api/mcp"
}
}
}远程端点
https://getyoutubetranscript.com/api/mcpstreamable-http它能做什么
工具清单
工具（7）
🟢get_youtube_transcript(video_url, language, send_metadata)
Fetch the full transcript for a YouTube video, plus its title/author/thumbnail metadata. Returns the complete spoken text as one block - this API does not provide per-segment timestamps, so don't ask for or expect a timestamped breakdown.
输入模式
{
"type": "object",
"properties": {
"video_url": {
"type": "string",
"description": "YouTube URL (full or short) or an 11-character video ID"
},
"language": {
"description": "Language code, e.g. 'en', 'es'. Defaults to 'en'.",
"type": "string"
},
"send_metadata": {
"description": "Include title/author/thumbnail metadata. Defaults to true.",
"type": "boolean"
}
},
"required": [
"video_url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢search_youtube(query, search_type, continuation)
Search YouTube for videos or channels. Paginate with `continuation` from a previous response.
输入模式
{
"type": "object",
"properties": {
"query": {
"description": "Search query. Required unless `continuation` is set.",
"type": "string"
},
"search_type": {
"description": "'video' (default) or 'channel'.",
"type": "string",
"enum": [
"video",
"channel"
]
},
"continuation": {
"description": "Opaque token from a previous response - fetches the next page. Do not construct this yourself.",
"type": "string"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_channel_latest_videos(channel)
Get a channel's metadata plus its most recent uploads. Free - no credits charged.
输入模式
{
"type": "object",
"properties": {
"channel": {
"type": "string",
"description": "Channel @handle, URL, or UC... id"
}
},
"required": [
"channel"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢search_channel_videos(channel, query, continuation)
Search within one channel's videos for a query. Paginate with `continuation` from a previous response.
输入模式
{
"type": "object",
"properties": {
"channel": {
"description": "Channel @handle, URL, or UC... id. Required unless `continuation` is set.",
"type": "string"
},
"query": {
"description": "Query to search within the channel. Required unless `continuation` is set.",
"type": "string"
},
"continuation": {
"description": "Opaque token from a previous response - fetches the next page.",
"type": "string"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_channel_videos(channel, continuation)
List every video a channel has uploaded (the /videos tab), paginated. Paginate with `continuation` from a previous response.
输入模式
{
"type": "object",
"properties": {
"channel": {
"description": "Channel @handle, URL, or UC... id. Required unless `continuation` is set.",
"type": "string"
},
"continuation": {
"description": "Opaque token from a previous response - fetches the next page.",
"type": "string"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_playlist_videos(playlist, continuation)
Get every video in a YouTube playlist, paginated. Paginate with `continuation` from a previous response.
输入模式
{
"type": "object",
"properties": {
"playlist": {
"description": "Playlist URL or id. Required unless `continuation` is set.",
"type": "string"
},
"continuation": {
"description": "Opaque token from a previous response - fetches the next page.",
"type": "string"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_credits
Check the remaining credit balance for this key/account. Free - never charged, does not affect the balance.
输入模式
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}社区
证据