MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Your curated sources (RSS, YouTube, podcasts, Google News) as context for any AI agent.
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.feednest.com在终端中运行这条命令
claude mcp add --transport http feednest https://mcp.feednest.com粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"feednest": {
"url": "https://mcp.feednest.com"
}
}
}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": {
"feednest": {
"type": "http",
"url": "https://mcp.feednest.com"
}
}
}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.feednest.com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。
服务器要求先登录,才会列出它的工具。
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
发布者(LucaIaconelli)不是仓库所有者(feednest-app);可能是其他人代为上架的
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
在 211 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
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 3 项适用的基础检查中通过了 2 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(1.1.0)于24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。
Your sources. Not the whole web. Ask your AI about your feeds - it already knows.
ChatGPT searches the internet. Perplexity crawls billions of pages. When you ask about your industry, your interests, your world - they give you everything except what matters.
[FeedNest](https://www.feednest.com) is different. Your AI works exclusively with the sources you choose: the blogs you trust, the publications you follow, the experts you believe in. No algorithmic noise. No black-box results. Intelligence grounded in your world.
This MCP server gives any AI assistant - ChatGPT, Codex, Claude, Gemini, Grok, Cursor, Windsurf, Cline, Le Chat, and more - direct access to your feeds, articles, highlights, notes, and tags through natural language.
Just ask. Your AI handles the rest.
https://mcp.feednest.comNo API key needed. ChatGPT handles the OAuth flow automatically.
Include FeedNest as an MCP tool in your API request:
{
"type": "mcp", "server_url": "https://mcp.feednest.com", "server_label": "feednest", "authorization": "fn_live_YOUR_API_KEY" }
The plugin bundles skills, MCP config, and brand assets in one install. It is not in the Codex plugin directory yet, so install it from this repository: see Local Installation in the Codex plugin README.
Add to ~/.codex/config.toml:
[mcp_servers.feednest]
url = "https://mcp.feednest.com" bearer_token_env_var = "FEEDNEST_API_KEY"
export FEEDNEST_API_KEY="fn_live_YOUR_API_KEY"
Or via CLI:
codex mcp add feednest --transport http https://mcp.feednest.com
FeedNest is listed in Claude's connectors directory.
No API key needed, and the connector follows your Claude account to Claude Desktop and the mobile apps.
To add it by URL instead, add a custom connector in Customize → Connectors with the URL https://mcp.feednest.com and leave OAuth Client ID and Secret empty.
The Claude plugin brings the FeedNest server, a skill that tells Claude how to use the tools well, and the /feednest:briefing command. It signs in with OAuth, so it works on every FeedNest plan.
/plugin marketplace add feednest-app/mcp
/plugin install feednest@feednest
Then run /mcp, pick feednest and sign in.
claude mcp add --transport http feednest https://mcp.feednest.com \
--header "Authorization: Bearer fn_live_YOUR_API_KEY"
Add -s user for global access across all projects. API keys need FeedNest Pro.
The directory connector above already works in Claude Desktop. To configure FeedNest in claude_desktop_config.json instead, which only runs stdio servers, use the mcp-remote bridge:
{
"mcpServers": { "feednest": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.feednest.com", "--header", "Authorization:${AUTH_HEADER}" ], "env": { "AUTH_HEADER": "Bearer fn_live_YOUR_API_KEY" } } } }
Config path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS), %APPDATA%\Claude\claude_desktop_config.json (Windows), or ~/.config/Claude/claude_desktop_config.json (Linux).
Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for global):
{
"mcpServers": { "feednest": { "url": "https://mcp.feednest.com", "headers": { "Authorization": "Bearer fn_live_YOUR_API_KEY" } } } }
Tip: Cursor supports env var interpolation:
"Bearer ${env:FEEDNEST_API_KEY}". Do not add a"type"field - Cursor auto-detects from the"url"key.
Available on all plans, including the free tier.
FeedNest, Server URL to https://mcp.feednest.comAPI Token Authentication, Authorization to Bearer fn_live_YOUR_API_KEYAdd to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": { "feednest": { "serverUrl": "https://mcp.feednest.com", "headers": { "Authorization": "Bearer fn_live_YOUR_API_KEY" } } } }
Important: Windsurf uses
"serverUrl"(not"url"). Using the wrong key causes a silent failure.
In VS Code, open Cline extension settings → MCP Servers configuration (JSON):
{
"mcpServers": { "feednest": { "type": "streamableHttp", "url": "https://mcp.feednest.com", "headers": { "Authorization": "Bearer fn_live_YOUR_API_KEY" } } } }
Critical: The
"type": "streamableHttp"field is mandatory for Cline. Without it, custom headers may fail silently and authentication won't work.
Add to ~/.gemini/settings.json:
{
"mcpServers": { "feednest": { "httpUrl": "https://mcp.feednest.com", "headers": { "Authorization": "Bearer fn_live_YOUR_API_KEY" } } } }
Note: Gemini CLI uses
"httpUrl"(not"url"). The"url"field is reserved for SSE transport. CLI only - gemini.google.com does not support external MCP servers.
Available through the xAI API/SDK only, not from the grok.com chat UI.
curl https://api.x.ai/v1/responses \
-H "Authorization: Bearer $XAI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "grok-3", "tools": [{ "type": "mcp", "server_url": "https://mcp.feednest.com", "server_label": "feednest", "authorization": "Bearer fn_live_YOUR_API_KEY" }], "input": "What are my unread articles?" }'
Any client supporting Streamable HTTP can connect using:
https://mcp.feednest.comAuthorization: Bearer fn_live_YOUR_API_KEYFor stdio-only clients, use the mcp-remote bridge:
{
"mcpServers": { "feednest": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.feednest.com", "--header", "Authorization:Bearer fn_live_YOUR_API_KEY" ] } } }
| Tool | Description | Key Parameters |
|---|---|---|
get_articles | List articles with title, source, date, and summary preview. Views: newsfeed, by-feed, by-folder, by-tag, tagged, highlighted, noted. | view\*, feed_id, folder_id, tag_id, limit, query, sort, unread_only, date_from, date_to, count_only |
get_article | Get full article content including highlights, notes, and reading time. | article_id\* |
extract_article | Fetch full content from the original URL when RSS truncated it. | article_id\* |
| Tool | Description | Key Parameters |
|---|---|---|
mark_as_read | Mark an article as read. | article_id\* |
mark_as_unread | Mark an article as unread. | article_id\* |
mark_all_as_read | Mark all articles as read, optionally filtered by feed or folder. | feed_id, folder_id |
| Tool | Description | Key Parameters |
|---|---|---|
save_article | Save an article for later reading. | article_id\* |
unsave_article | Remove an article from saved items. | article_id\* |
save_url | Save an external URL for later reading. | url\* |
get_saved | List saved articles with search, date filtering, and sorting. | limit, query, sort, date_from, date_to |
| Tool | Description | Key Parameters |
|---|---|---|
get_feeds | List subscribed feeds with unread counts. Search by name. | folder_id, query, limit |
get_folders | List all feed folders with feed counts. | - |
get_tags | List all tags with article counts. | - |
| Tool | Description | Key Parameters |
|---|---|---|
create_tag | Create a new tag for categorizing articles. | name\*, color |
delete_tag | Delete a tag by ID. | tag_id\* |
tag_article | Add or remove a tag on an article. | article_id\*, tag_id\*, action\* (add/remove) |
| Tool | Description | Key Parameters |
|---|---|---|
get_highlights | Get all text highlights from an article. | article_id\* |
add_highlight | Highlight a text passage. The text must exist exactly in the article. | article_id\*, text\*, color |
remove_highlight | Remove a highlight from an article. | article_id\*, highlight_id\* |
| Tool | Description | Key Parameters |
|---|---|---|
get_notes | Get the note on an article. | article_id\* |
add_note | Add or update a note on an article. | article_id\*, content\* |
delete_note | Delete a note from an article. | article_id\* |
| Tool | Description | Key Parameters |
|---|---|---|
get_recently_read | Get recently opened articles. Supports search and date filtering. | limit, since, date_to, query, sort |
| Tool | Description | Key Parameters |
|---|---|---|
get_output_feeds | List public RSS output feeds created by the user. | - |
text_to_speech is not exposed by the hosted MCP server: it generates audio with an AI model, which the Claude connectors directory does not allow. Reading articles aloud stays availabl
只显示了开头部分;其余内容请在仓库中阅读