MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Independent, unofficial project for YouTube metadata, transcripts, comments, and search.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
YT_PROVIDER, YOUTUBE_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"youtube": {
"command": "npx",
"args": [
"-y",
"@granitebps/youtube-mcp"
],
"env": {
"YT_PROVIDER": "your-value",
"YOUTUBE_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add youtube --env YT_PROVIDER=your-value --env YOUTUBE_API_KEY=your-value -- npx -y @granitebps/youtube-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"youtube": {
"command": "npx",
"args": [
"-y",
"@granitebps/youtube-mcp"
],
"env": {
"YT_PROVIDER": "your-value",
"YOUTUBE_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"youtube": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@granitebps/youtube-mcp"
],
"env": {
"YT_PROVIDER": "your-value",
"YOUTUBE_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
YT_PROVIDER env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过 GitHub 账户 granitebps 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:YOUTUBE_API_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.1.1)于19天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
YouTube MCP lets an MCP client read YouTube video metadata, caption transcripts, comments, and search results. By default it needs no YouTube API key or account; an optional official YouTube Data API provider serves metadata, comments, and search with an API key.
Supports both stdio (local) and Streamable HTTP (VPS/remote) transports.
This is an independent, unofficial open-source project. It is not affiliated with, endorsed by, or sponsored by YouTube or Google.
innertube provider serves metadata, comments, and search through youtubei.js, using an unofficial/internal YouTube interface without a YouTube Data API key. Unofficial access may change, break, be restricted, or be blocked.YT_PROVIDER=api and supply your own YOUTUBE_API_KEY to use the official YouTube Data API v3 for those three tools.youtube-transcript-plus, regardless of YT_PROVIDER. Transcript retrieval remains unofficial and does not use the official Data API path or your API key.Users are responsible for deciding whether an access method suits their use and for complying with applicable service terms and law. See access methods and service terms for the tool/backend mapping, BYOK setup, limitations, and software licenses.
| Tool | Description |
|---|---|
search_youtube | Search videos with filters for upload date and popularity |
get_video_info | Video metadata: title, channel, description, duration, views, likes, upload date, tags |
get_video_comments | Comment threads with author info, likes, and the replies YouTube includes |
get_video_transcript | Transcripts (manual + auto-generated captions) with timestamps |
get_transcript_languages | Lists available manual and auto-generated caption languages |
get_server_info | Server version, active provider, and the backend serving each tool |
No YouTube API key required by default. The default
innertubeprovider usesyoutubei.js(an unofficial/internal YouTube interface) for video info, comments, and search. Transcripts always useyoutube-transcript-plus. Neither needs an API key or authentication. See Providers for the optional official API.
Your MCP client can run the published package without a clone:
npx -y @granitebps/youtube-mcp
The server uses stdio. Keep stdout reserved for MCP traffic.
To develop the server or use a clone directly:
git clone https://github.com/granitebps/youtube-mcp.git
cd youtube-mcp npm ci npm run build
Point your MCP client at the compiled entry point:
node /absolute/path/to/youtube-mcp/dist/index.js
Run npm run build after each source change. Do not use src or npm run dev as the client's stdio command; build output on stdout can corrupt MCP messages.
Each example starts with the npm package, followed by the local equivalent. Replace /absolute/path/to/youtube-mcp with your clone's path. Settings from Configuration can be added as environment variables.
Add the npm package to Claude Code:
claude mcp add youtube -- npx -y @granitebps/youtube-mcp
For a local build:
claude mcp add youtube -- node /absolute/path/to/youtube-mcp/dist/index.js
Claude Code uses local scope by default. Add --scope user before youtube to make the server available across projects.
Claude Desktop reads the same server from claude_desktop_config.json (on macOS, ~/Library/Application Support/Claude/claude_desktop_config.json). Restart the app after editing the file.
{
"mcpServers": { "youtube": { "command": "npx", "args": ["-y", "@granitebps/youtube-mcp"] } } }
For a local build, replace command and args with:
{
"command": "node", "args": ["/absolute/path/to/youtube-mcp/dist/index.js"] }
Add the npm package to ~/.codex/config.toml, or to .codex/config.toml in a trusted project:
[mcp_servers.youtube]
command = "npx" args = ["-y", "@granitebps/youtube-mcp"]
For a local build:
[mcp_servers.youtube]
command = "node" args = ["/absolute/path/to/youtube-mcp/dist/index.js"]
Restart Codex after editing the file.
Add the npm package to opencode.json or opencode.jsonc:
{
"$schema": "https://opencode.ai/config.json", "mcp": { "youtube": { "type": "local", "command": ["npx", "-y", "@granitebps/youtube-mcp"], "enabled": true } } }
For a local build, replace the command array with:
{
"command": ["node", "/absolute/path/to/youtube-mcp/dist/index.js"] }
Add the npm package to .cursor/mcp.json in a project, or to ~/.cursor/mcp.json for global use:
{
"mcpServers": { "youtube": { "command": "npx", "args": ["-y", "@granitebps/youtube-mcp"] } } }
For a local build, replace command and args with:
{
"command": "node", "args": ["/absolute/path/to/youtube-mcp/dist/index.js"] }
Add to your VS Code settings.json:
{
"mcp": { "servers": { "youtube": { "command": "npx", "args": ["-y", "@granitebps/youtube-mcp"] } } } }
For remote deployment, the server runs as a persistent HTTP service using the Streamable HTTP transport (the current MCP standard, replacing the deprecated SSE transport).
# On your VPS
git clone https://github.com/granitebps/youtube-mcp.git cd youtube-mcp npm ci npm run build
cp .env.example .env
YouTube often blocks datacenter IPs. If get_video_info returns ACCESS_BLOCKED with "Sign in to confirm you're not a bot", set YT_PROVIDER=api and YOUTUBE_API_KEY to serve metadata, comments, and search through the official API. See Providers.
# Using --http flag
node dist/index.js --http
TRANSPORT=http PORT=3000 node dist/index.js
npm run start:http
The server will listen on http://0.0.0.0:3000/mcp.
server {
listen 443 ssl; server_name mcp.yourdomain.com;
ssl_certificate /etc/letsencrypt/live/mcp.yourdomain.com/fullchain.pem; ssl_certificate_key /etc/letsencrypt/live/mcp.yourdomain.com/privkey.pem;
location /mcp { proxy_pass http://127.0.0.1:3000/mcp; proxy_http_version 1.1; proxy_set_header Host $host; proxy_set_header X-Real-IP $remote_addr; proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; proxy_set_header X-Forwarded-Proto $scheme;
proxy_set_header Connection ''; proxy_buffering off; proxy_cache off; chunked_transfer_encoding on; } }
Get a free TLS certificate:
sudo apt install certbot python3-certbot-nginx
sudo certbot --nginx -d mcp.yourdomain.com
Create /etc/systemd/system/youtube-mcp.service:
[Unit]
Description=YouTube MCP Server After=network.target
[Service] Type=simple User=your_user WorkingDirectory=/path/to/youtube-mcp ExecStart=/usr/bin/node dist/index.js --http Restart=always RestartSec=5 Environment=TRANSPORT=http Environment=PORT=3000 Environment=HOST=127.0.0.1
[Install] WantedBy=multi-user.target
sudo systemctl daemon-reload
sudo systemctl enable youtube-mcp sudo systemctl start youtube-mcp sudo systemctl status youtube-mcp
{
"mcp": { "servers": { "youtube": { "type": "http", "url": "https://mcp.yourdomain.com/mcp" } } } }
{
"mcpServers": { "youtube": { "type": "streamable-http", "url": "https://mcp.yourdomain.com/mcp" } } }
Once connected, you can ask your AI agent things like:
All tools return:
content: short human-readable text for chat-style MCP clientsstructuredContent: JSON-shaped data for agents that need reliable fieldsThe server is intentionally JSON-first, text-second. Agents should prefer structuredContent when they need to filter, transform, or chain tool results.
Example shape from get_video_info:
{
"content": [ { "type": "text", "text": "📹 Example title\n\nChannel: Example channel\n..." } ], "structuredContent": { "videoId": "dQw4w9WgXcQ", "title": "Example title", "description": "Example description", "channelName": "Example channel", "channelId": "UC123", "uploadedAt": "Sep 14, 2017", "duration": "3m 33s", "durationSeconds": 213, "viewCount": "123456", "likeCount": "7890", "commentCount": null, "tags": ["music", "pop"], "thumbnailUrl": "https://..." } }
Values YouTube did not provide are null, never placeholders such as "0", "N/A" or "Unknown".
Failures return isError: true. The text starts with a code (❌ [ACCESS_BLOCKED] ...) and _meta["youtube-mcp/error"] carries the details:
{
"isError": true, "content": [{ "type": "text", "text": "❌ [ACCESS_BLOCKED] YouTube requires sign-in to access video C7OQHIpDlvA: Sign in to confirm you’re not a bot" }], "_meta": { "youtube-mcp/error": { "code": "ACCESS_BLOCKED", "message": "...", "retryable": false, "upstream": { "playabilityStatus": "LOGIN_REQUIRED", "reason": "Sign in to confirm you’re not a bot", "accessKind": "login_required" } } } }
The error is in _meta, not structuredContent, because MCP SDK clients validate any structuredContent against the tool's output schema, even on error results.
| Code | Meaning |
|---|---|
INVALID_INPUT | Not a YouTube URL or 11-character video ID, or an invalid language code |
ACCESS_BLOCKED | YouTube refused this client: HTTP 429/403, CAPTCHA, consent page, sign-in or bot check. upstream.accessKind is rate_limited, forbidden, login_required, consent_required, or quota_exceeded (official API quota used up). Says nothing about whether the video exists or has captions |
| VIDEO_UNAVAILABLE | YouTube reports the video as ERROR, UNPLAYABLE, private or offline. upstream.reason is
只显示了开头部分;其余内容请在仓库中阅读