MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
PageRankCafe MCP server: create and post ads, read performance, query platform insights.
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。
PAGERANKCAFE_API_KEY, PAGERANKCAFE_BASE_URL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": {
"pagerankcafe": {
"command": "npx",
"args": [
"-y",
"pagerankcafe-mcp"
],
"env": {
"PAGERANKCAFE_API_KEY": "your-value",
"PAGERANKCAFE_BASE_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add pagerankcafe --env PAGERANKCAFE_API_KEY=your-value --env PAGERANKCAFE_BASE_URL=your-value -- npx -y pagerankcafe-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": {
"pagerankcafe": {
"command": "npx",
"args": [
"-y",
"pagerankcafe-mcp"
],
"env": {
"PAGERANKCAFE_API_KEY": "your-value",
"PAGERANKCAFE_BASE_URL": "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": {
"pagerankcafe": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"pagerankcafe-mcp"
],
"env": {
"PAGERANKCAFE_API_KEY": "your-value",
"PAGERANKCAFE_BASE_URL": "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。
PAGERANKCAFE_BASE_URL 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7日
注册名称已通过域名 pagerankcafe.com 验证(注册中心会核实域名所有权)
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:PAGERANKCAFE_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(0.1.3)于2个月前进入注册中心。
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。
The marketing platform for your AI agents.
An MCP (Model Context Protocol) server for the PageRankCafe API. It gives an AI agent tools to read and post link ads, banner ads, YouTube video ads, and press releases/blog articles on PageRankCafe, check credit and referral balances, read per-placement performance, and (on paid tiers) pull platform-wide ad performance insights.
Account creation and key generation are both manual, human steps on the website — there is no programmatic signup.
The server reads its configuration from environment variables:
| Variable | Required | Default | Description |
|---|---|---|---|
PAGERANKCAFE_API_KEY | Yes | — | Your API key from /apiKeys. The server exits immediately with an error if this is not set. |
PAGERANKCAFE_BASE_URL | No | https://pagerankcafe.com | API base URL. Override only for testing against a non-production environment. |
Add to your claude_desktop_config.json:
{
"mcpServers": { "pagerankcafe": { "command": "npx", "args": ["-y", "pagerankcafe-mcp"], "env": { "PAGERANKCAFE_API_KEY": "your-api-key-here" } } } }
claude mcp add pagerankcafe --env PAGERANKCAFE_API_KEY=your-api-key-here -- npx -y pagerankcafe-mcp
Add to your Cursor MCP settings (~/.cursor/mcp.json or the project's .cursor/mcp.json):
{
"mcpServers": { "pagerankcafe": { "command": "npx", "args": ["-y", "pagerankcafe-mcp"], "env": { "PAGERANKCAFE_API_KEY": "your-api-key-here" } } } }
Every write tool and the insights tool require a paid membership (Bronze/Silver/Gold); the API returns an error for free accounts. Read tools work on any valid key, including free accounts.
| Tool | Membership | Description |
|---|---|---|
health | Free | Checks API connectivity and returns the authenticated user's username and membership status. |
list_links | Free | Lists your active link ads. |
list_banners | Free | Lists your active banner ads. |
list_youtube_ads | Free | Lists your active YouTube video ads. |
list_press_releases | Free | Lists your active press releases / blog articles. |
get_credits | Free | Returns your credit balance, available post slots, links viewed, and links remaining. |
get_referral_stats | Free | Returns your referral counts (today, 7 day, 30 day, all time). |
list_posts | Free | Returns per-placement performance for link, banner, YouTube, or press-release ads. |
upload_image | Paid | Uploads an image (local file path or base64) and returns a hosted HTTPS URL. |
create_banner | Paid | Creates a new banner ad. |
post_banner | Paid | Posts an existing banner into rotation using credits. |
create_youtube_ad | Paid | Creates a new YouTube video ad. |
update_youtube_ad | Paid | Partially updates an existing YouTube ad you own. |
create_press_release | Paid | Creates a new press release / blog article. |
update_press_release | Paid | Partially updates an existing press release you own. |
post_press_release | Paid | Posts an existing press release to the home-page widget using credits. |
create_link | Paid | Creates a new link ad. |
post_link | Paid | Posts an existing link ad into rotation using credits (free/credit posts only: ad_days must be 0; view_time/view_credits are derived server-side from icon/bold/double_time, not accepted as input). Returns status: "active" when the post goes live immediately, or status: "pending" (with an explanatory message) when the posting user needs approval first. |
get_platform_insights | Paid | Trailing-30-day platform performance aggregates by ad type and option, plus current prices. |
Full request/response detail for each underlying endpoint is in the OpenAPI spec at https://pagerankcafe.com/api/spec (rendered at https://pagerankcafe.com/api/docs).
Every tool returns the API's JSON response as the tool result on success. On a non-2xx API response, the tool returns an MCP tool error (isError: true) carrying the API's error message. There are no retries and no silent fallbacks — a failed call always surfaces as a failed tool call.
npm install
npm run build # compiles src/ to dist/ with tsc npm test # builds, then runs the stdio smoke test (no network required)
The test starts the built server as a subprocess over stdio (using StdioClientTransport from @modelcontextprotocol/sdk), lists its tools, and checks the full tool list is present — no real API key or network access is used.