MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Hosted, read-only Google Analytics 4 MCP: reports, period comparisons, realtime, custom fields.
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。
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.querysail.com/ga4/mcp在终端中运行这条命令
claude mcp add --transport http ga4 https://mcp.querysail.com/ga4/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"ga4": {
"url": "https://mcp.querysail.com/ga4/mcp"
}
}
}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": {
"ga4": {
"type": "http",
"url": "https://mcp.querysail.com/ga4/mcp"
}
}
}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.querysail.com/ga4/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 querysail.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。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.0.0)于26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。
QuerySail is a hosted MCP server for Google Analytics 4. Connect it to ChatGPT, Claude, Codex, Cursor or VS Code, sign in, connect your Google account once, and ask about your traffic, engagement and conversions in plain language. There is nothing to install, no Google Cloud project and no API key to paste.
https://mcp.querysail.com/ga4/mcp (Streamable HTTP, OAuth 2.1 with dynamic client registration)This repository holds the public listing files (MCP Registry server.json, a Claude Code plugin, client configs). The service itself is hosted at querysail.com; its source is not published here.
All tools are read-only. QuerySail cannot create or edit properties, data streams, key events, audiences or any other Google Analytics setting.
| Tool | What it does |
|---|---|
list_properties | Lists the Google Analytics 4 properties your connected Google accounts can read, with exact property IDs and their Analytics accounts. |
list_fields | Lists the dimensions and metrics a property can report on, including its custom dimensions, custom metrics and key events. |
run_report | Users, sessions, views, engagement, events, key events, revenue and any other Data API metric, broken down by date, channel, source/medium, landing page, page, country, device, event and more, with filters. |
compare_report | Compares two periods (previous period, same weekdays a year earlier, or custom dates) and lists the channels, sources, pages or countries that gained or lost the most. |
run_realtime_report | Active users, views and events in the last 30 minutes, by country, city, device, page or event. |
You need a QuerySail account with Google Analytics connected: sign up at https://querysail.com and choose Connect Google Analytics under Account → Connections. Each client below opens a browser window to sign in the first time.
claude mcp add --transport http --scope user querysail-ga4 https://mcp.querysail.com/ga4/mcp
Then run /mcp, choose querysail-ga4 and sign in. Or install it as a plugin, which also adds a Google Analytics analysis skill:
/plugin marketplace add querysail/querysail-ga4
/plugin install querysail-ga4@querysail-ga4
Open Customize → Connectors, select + Add → Add custom connector, name it QuerySail GA4 and paste https://mcp.querysail.com/ga4/mcp as the server URL.
Turn on Developer mode under Settings → Security and login, go to chatgpt.com/plugins, select the plus button and paste the endpoint as the connection URL.
codex mcp add querysail-ga4 --url https://mcp.querysail.com/ga4/mcp
codex mcp login querysail-ga4
Add to ~/.cursor/mcp.json:
{
"mcpServers": { "querysail-ga4": { "url": "https://mcp.querysail.com/ga4/mcp" } } }
Run MCP: Add Server, choose HTTP and paste the endpoint, or add to mcp.json:
{
"servers": { "querysail-ga4": { "type": "http", "url": "https://mcp.querysail.com/ga4/mcp" } } }
Open MCP Servers → Remote Servers, name it querysail-ga4, paste the endpoint, choose Streamable HTTP and click Add Server. Or add to cline_mcp_settings.json:
{
"mcpServers": { "querysail-ga4": { "type": "streamableHttp", "url": "https://mcp.querysail.com/ga4/mcp" } } }
Sign in with your QuerySail account when Cline asks.
Use the mcp-remote bridge (needs Node.js):
{
"mcpServers": { "querysail-ga4": { "command": "npx", "args": ["mcp-remote", "https://mcp.querysail.com/ga4/mcp"] } } }
The querysail-google-analytics skill tells coding agents such as Claude Code, Codex, Cursor and OpenCode which QuerySail tool to call for each question and how to report the numbers. Install it with the skills CLI (needs Node.js):
npx skills add https://querysail.com --skill querysail-google-analytics
analytics.readonly scope, granted separately from Search Console. Refresh tokens are encrypted at rest. You can hide properties, disconnect Google or delete your account at any time.The files in this repository are MIT licensed. The QuerySail service is subject to its terms.