MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Manage business listings, reviews, posts and local analytics across 50 plus sites
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。
Authorization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 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http listingsapi https://listingsapi.com/mcp --header 'Authorization: your-value'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": {
"listingsapi": {
"url": "https://listingsapi.com/mcp",
"headers": {
"Authorization": "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": {
"listingsapi": {
"type": "http",
"url": "https://listingsapi.com/mcp",
"headers": {
"Authorization": "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。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 必填 HTTP header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 listingsapi.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:Authorization
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38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。
Listings API MCP
Connect any MCP capable AI assistant to the Listings API and manage business listings, reviews, posts and local analytics across 50 plus directories, maps and search engines.
Website · API docs · MCP page · Claude directory · Get an API key · Apify actors
Local search runs on business data. A shop, a clinic or a franchise outlet has a name, an address, a phone number, opening hours, categories and photos, and that data has to be identical on Google, Apple Maps, Bing, Facebook, Yelp, the voice assistants and dozens of smaller directories before search engines trust it enough to rank it. Keeping that data consistent by hand does not scale past a handful of locations.
The Listings API is a REST API that does this job. You store each location once, and the API syncs it to more than 50 publishers, tracks where each listing is live, finds and suppresses duplicates, pulls in the reviews those listings collect, lets you reply to them, publishes posts and offers to the connected profiles, and returns the performance data Google, Facebook and Bing report back. Agencies, multi location brands and franchise systems use it to run local presence for hundreds or thousands of locations from one place.
The Model Context Protocol lets an AI assistant call external tools. This server exposes the Listings API as a set of MCP tools, so an assistant such as Claude, Cursor, Windsurf, Gemini CLI or Cline can look up your locations, read your reviews, draft and publish replies, schedule posts and pull analytics in plain conversation, using your own account and your own data.
It is a remote server. It runs at https://listingsapi.com/mcp and uses Streamable HTTP. No local server package or build is required. Point your client at the URL and sign in through its OAuth browser flow, or use an existing API key where the client requires a header.
https://listingsapi.com/mcp
The same server is listed in these directories, so you can install it from the one your client already uses:
| Directory | Listing |
|---|---|
| Claude | claude.ai/directory/listings-api |
| Official MCP Registry | com.listingsapi/mcp |
| Cursor | cursor.directory/plugins/listings-api |
| Glama | glama.ai/mcp/connectors/com.listingsapi/mcp |
| Smithery | smithery.ai/servers/support-hxau/listingsapi |
| MCP.so | mcp.so/servers/listings-api |
| mcpservers.org | mcpservers.org/servers/listings-api/listingsapi-mcp |
The agent skills in this repository are listed separately; see Agent skills.
Once connected, the assistant can work across five areas of your account.
Locations. Create and update location profiles, search for locations, and read their details. A location is the master record used by its publisher listings.
Listings and citations. See which publishers currently carry a location and what state each listing is in, list the sites your plan covers, pull the duplicate listings the network has detected for one location or for your whole account, and mark a listing as a duplicate so it gets suppressed, or clear that flag if the match was wrong. Voice assistant coverage is reported separately.
Reviews. Read reviews, fetch specific reviews by ID, inspect review analytics, and publish replies where the connected publisher supports them. Published replies appear on the review site.
Posts. Read existing posts and publish posts to supported connected profiles. Check the current tool contract for supported publishers and payloads.
Analytics. Read Google, Facebook and Bing performance for any location: search views, map views, direction requests, calls, website clicks and the rest, for whatever date range you ask about.
There is also a set of connected account operations for linking a Google or Facebook account, matching its profiles to your locations and creating a brand new Google Business Profile listing for a location that has none.
Destructive operations such as archiving locations and deleting posts are not exposed as MCP tools. Use the MCP guide and the server's documentation tools to check the operations currently available.
Once the server is connected, these are the kinds of things you can ask your assistant.
A ListingsAPI account. See plans and signup for production access, or check Day Pass availability below. OAuth-capable clients let you sign in without copying an API key into a configuration file.
Check live availability before signup; the Day Pass is offered for limited periods. While open is true, you can activate a free 24-hour sandbox at Day Pass signup. It covers up to 2 locations and syncs to 10 ListingsAPI demo directories. It never writes to real publishers. Reviews, posts, social, analytics, connected accounts, and webhooks are excluded.
Signup asks for your name, email, and company, plus acceptance of the Terms of Service and Privacy Policy. The 24 hours begin when you activate the pass through the emailed link or 6-digit code. Read the Day Pass guide for current limits and activation steps. In an OAuth client, choose Email me a sign-in link with the Day Pass email. For API-key clients, configure the Day Pass key locally using the same API header prefix. Installing a plugin or skill does not start a pass.
Keys carry an access level. A key with Read access covers every lookup and report. Creating and updating locations, replying to reviews, publishing posts and connecting accounts need a key with Write access.
The server accepts two ways of authenticating:
| Method | Header | Use it when |
|---|---|---|
| OAuth 2.0 | Managed by your client | Your client supports the browser sign-in and consent flow |
| API key | Authorization: API | Your client requires a static header; enter the key only in local settings |
OAuth uses public clients, PKCE, and dynamic client registration. No pre-issued client secret is needed. Start with read access unless your task requires writes. OAuth tokens apply to the MCP endpoint; REST integrations use API keys.
Use the client instructions below. Replace API-key placeholders only in local settings, and keep credentials out of shared repositories.
In Add plugin marketplace, enter:
| Field | Value |
|---|---|
| Source | https://github.com/listings-api/listingsapi-mcp.git |
| Git ref | main |
| Sparse paths | Leave empty |
Choose the Listings API marketplace and install Listings API. Complete the browser sign-in and consent flow when prompted. The plugin connects to https://listingsapi.com/mcp and includes the six agent skills already in this repository. Installation does not create a ListingsAPI account or activate a Day Pass.
To register the same marketplace from the Codex CLI:
codex plugin marketplace add https://github.com/listings-api/listingsapi-mcp.git --ref main
The catalog is .agents/plugins/marketplace.json, and the Codex compatibility manifest is .codex-plugin/plugin.json. They reuse the existing skills, logo, and MCP configuration. Keep sparse paths empty so those files remain available. This repo marketplace is separate from the public OpenAI plugin directory; see the official packaging documentation.
claude mcp add --transport http listingsapi https://listingsapi.com/mcp --header "Authorization: API <your-api-key>"
Open claude.ai/directory/listings-api and click Connect. Claude runs the sign-in flow and the connector is ready in Claude Desktop and Claude.ai.
To add it by URL instead, open Settings, then Connectors, then Add custom connector, and enter https://listingsapi.com/mcp as the URL. Claude Desktop will prompt for authentication when the server first requests it.
Install it from Cursor Directory, or add to ~/.cursor/mcp.json, or to .cursor/mcp.json inside a project:
{
"mcpServers": { "listingsapi": { "url": "https://listingsapi.com/mcp" } } }
Use Connect on the server entry to complete OAuth in your browser. This repository's Cursor plugin uses the same configuration. If you need API-key authentication, add "headers": { "Authorization": "API " } inside the entry in local settings.
Open the MCP configuration file from your editor's MCP settings; the legacy Windsurf location is ~/.codeium/windsurf/mcp_config.json. Editor versions can use a different path. For a client that supports OAuth, add:
{
"mcpServers": { "listingsapi": { "serverUrl": "https://listingsapi.com/mcp" } } }
Complete the browser authentication prompt. For API-key authentication, add "headers": { "Authorization": "API " } inside the entry in local settings. See the current Cascade MCP documentation for your editor version.
Install this repository as an extension:
gemini extensions install https://github.com/listings-api/listingsapi-mcp
Restart Gemini CLI, then run /mcp auth listingsapi and complete the browser sign-in. Use /mcp to inspect the connection and discovered tools. The extension enables OAuth and needs no API-key setting.
For an API-key setup instead of the extension, add this entry to the existing mcpServers object in ~/.gemini/settings.json:
{
"mcpServers": { "listingsapi": { "httpUrl": "https://listingsapi.com/mcp", "headers": { "Authorization": "API ${LISTINGSAPI_API_KEY}" } } } }
Provide LISTINGSAPI_API_KEY through your local environment. Use one connection configuration at a time. See Gemini's MCP documentation for authentication and configuration details.
Open MCP Servers, then Remote Servers, add https://listingsapi.com/mcp, and
只显示了开头部分;其余内容请在仓库中阅读