MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Access your app analytics, ASO tools, and app market intelligence with Appfigures.
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。
APPFIGURES_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 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.appfigures.com/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"appfigures": {
"command": "npx",
"args": [
"-y",
"@appfigures/cli",
"mcp"
],
"env": {
"APPFIGURES_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http appfigures https://mcp.appfigures.com/mcpclaude mcp add appfigures --env APPFIGURES_API_KEY=your-value -- npx -y @appfigures/cli 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": {
"appfigures": {
"url": "https://mcp.appfigures.com/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"appfigures": {
"command": "npx",
"args": [
"-y",
"@appfigures/cli",
"mcp"
],
"env": {
"APPFIGURES_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": {
"appfigures": {
"type": "http",
"url": "https://mcp.appfigures.com/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"appfigures": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@appfigures/cli",
"mcp"
],
"env": {
"APPFIGURES_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。
ChatGPT 只能连接互联网上的服务器:
https://mcp.appfigures.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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6日
注册名称已通过域名 appfigures.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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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:APPFIGURES_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(4.0.0)于28天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
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 Appfigures CLI — query app metrics, reviews, and store data from your terminal.
Try it now without installing:
npx @appfigures/cli auth login
npx @appfigures/cli apps search "youtube"
Bring Appfigures into your agent however it's built — as tools it calls, code it writes, a CLI, or over MCP. Whichever you pick, you can do the same things and get the same JSON back.
@appfigures/clinpm install -g @appfigures/cli
Requires Node.js 22+. Works with pnpm and yarn too.
appfigures auth login
appfigures --help
Also available as af alias.
af auth login --interactive opens your browser in a guided flow; approve and paste the code back.af auth login prints an authorization URL — open it, approve, and finish with af auth login --code using the code shown. An agent can drive this end to end. For unattended use, set APPFIGURES_API_KEY instead: create a token at appfigures.com/developers/keys by clicking Create a New Client, then Create Personal Access Token.Either login saves the token to your OS credential manager (macOS Keychain, Windows Credential Manager, Linux Secret Service). See Environment for APPFIGURES_API_KEY and other overrides.
Appfigures runs a hosted Model Context Protocol server at https://mcp.appfigures.com/mcp. Add it to any MCP client that supports remote servers and sign in with your Appfigures account when the client asks. There's nothing to install and no token to manage.
Claude Code. Add it with one command, then run /mcp to sign in:
claude mcp add --transport http appfigures https://mcp.appfigures.com/mcp
Claude (web and desktop). Add the URL as a custom connector. See Add a connector that isn't in the directory.
ChatGPT. Add the URL as a custom MCP server with OAuth. See Connecting Appfigures to ChatGPT.
Other clients. Add a remote (Streamable HTTP) server with the same URL. See your client's MCP documentation for where.
The hosted server shares Public Data access and credits with the API and CLI. For request limits and credit costs, see Appfigures API, CLI, and MCP: Access, Limits, and Public Data.
For scripts and headless agents that authenticate with APPFIGURES_API_KEY, run the af commands directly, or use @appfigures/agent-toolkit from code.
af mcp (deprecated)af mcp runs the same tools as a local stdio server. It's deprecated and will be removed in the next major release. Existing setups keep working until then, but it won't get new MCP features. Move to the hosted server above.
Find apps and look up their identity. Other commands take the app IDs these return.
| Command | Description |
|---|---|
| af apps search | Find apps by name or publisher. Returns one row per unified app. Default returns Apple and Google listings; pass --all-stores to include other storefronts. To filter apps by estimate values (e.g. apps with >100k downloads last month) use explorer list-products. For estimates broken down by time, country, or storefront, use metrics query with datasets estimates.sales or estimates.revenue. |
| af apps get | Get an app's record: basic metadata (name, developer, etc) and, if the user tracks it, what data they can access. Pass a product ID for one storefront; unified app ID for all storefronts together. |
| af apps tracked | List the apps your Appfigures account tracks. |
| af apps breakdown | Count your tracked apps by data group (e.g. sales, usage, ranks, reviews, keywords), storefront, monetization model, and source (yours vs tracked competitors), plus the total and earliest release date. |
Search and analyze the full app catalog: millions of products across Apple, Google Play, Amazon, and other major stores, with 120+ fields spanning identity, storefront and country availability, categories, ratings, release dates, chart ranks, download and revenue estimates, SDK presence, demographics, and related apps.
| Command | Description |
|---|---|
| af explorer list‑products | Read catalog fields for one app or many. Fields referenced by query or sort come back automatically; pass --extra-fields for more. Use ["match","product_id", ] for a single app, or combine filters for population queries (e.g. iOS apps using Firebase with $1M+ US revenue). The 120+ fields span ranks, ratings, download and revenue estimates, SDKs, demographics, and more; query grammar and field list in docs get catalog_playbook. |
| af explorer aggregate‑products | Aggregate across the full catalog of millions of products across Apple, Google Play, Amazon, and other major stores: counts, averages, min/max, and histograms over any set of matching products. Uses the same query grammar as explorer list-products; returns aggregates, not product records. For market sizing, benchmarking, and segment analysis. |
| af explorer describe‑fields | List the catalog fields and the current user's access level for each. Search by keyword to find fields. Same field set explorer list-products and explorer aggregate-products accept. |
Query numeric datasets across dimensions.
| Command | Description |
|---|---|
| af metrics query | Query any numeric dataset for one or more apps. Optionally grouped by up to two dimensions, returned as a nested partition tree, not app records. Independently filterable by country, device type, and date range. filterAppsBy* options narrow the app set (by ID, storefront, source, or type); without one, a query covers every app the account tracks. |
| af metrics describe‑datasets | List every numeric dataset metrics query accepts, one row per dataset with its value type and whether it's limited to your own apps. |
App store presence: listing content, category ranks, top charts, and featured placements.
| Command | Description |
|---|---|
| af store app‑ranks | Trace rank history for one or more apps across countries, device types, category subtypes, and categories, as time-series positions with day-over-day deltas. |
| af store top‑charts | List the top apps in a category chart for a given country and category, with current positions and day-over-day deltas. |
| af store categories | List every store category with its ID. Numeric category IDs required by store app-ranks --category-ids and store top-charts --category-id are available here. |
| af store featured | List featured and editorial placements for an app or storefront product. Request 0 rows for summary stats only. |
| af store app‑listing | Read the full store listing for one storefront: localized text (name, subtitle, description, release notes) plus screenshots, video, categories, monetization, supported devices, country availability, price, ratings, file size, and age rating. Takes a numeric product ID (one storefront at a time; a unified app has one product per storefront). One locale per request. |
Who an app's users are and what else they use. Covers estimated age and gender, plus audience overlap with other apps.
| Command | Description |
|---|---|
| af audience demographics | Read an app's audience demographics: the estimated age and gender breakdown. |
| af audience cross‑usage | Find the apps that an app's users also use. |
Search, summarize, and reply to iOS and Google Play app store reviews.
| Command | Description |
|---|---|
| af reviews list | Read individual reviews for one or more apps. Returns review text, star rating, country, app version, and your response. Filterable by star rating, date range, country, version, response status, and tracking relationship. |
| af reviews breakdown | Aggregate review counts for one or more apps, bucketed by dimension. Returns one count per dimension value, plus a global total across the matched set. |
| af reviews reply | Post or withdraw a developer response on a specific review. Pass content to post; pass delete: true to withdraw a previously-posted response. |
Keyword visibility, rank tracking, and discovery across organic search (App Store, Google Play) and Apple Ads.
| Command | Description |
|---|---|
| af keywords organic | Check the organic keywords one or more apps rank for, with position, popularity, and competitiveness. |
| af keywords paid | List the paid keywords one or more apps run ads on, with impression share and organic rank. |
| af keywords tracked‑ranks | View where all your tracked keywords rank for a single app+country combo, with each keyword's current position, movement since it last changed, starting position, popularity, and competitiveness. |
| af keywords tracked
只显示了开头部分;其余内容请在仓库中阅读