Yt Azure MCP

MCP搜索检索

提供方 danielsegan

搜索检索 stdio · 本地进程 API Key 社区 / 第三方 Cursor
查看接入方式

一个用于搜索John Savill的YouTube频道中与Azure相关视频的MCP服务器,适用于Azure学习和技术查询。

一句话选型结论

按资料字段整理

Yt Azure MCP 属于搜索检索类 MCP 服务器,stdio · 本地进程,API Key,可直接接入 Cursor,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类搜索检索 传输方式stdio · 本地进程 鉴权API Key 部署方式本地部署
GitHub 星标 0 仓库热度,无公开仓库时显示未标注
工具数 5 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

搜索检索
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量5暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

YouTube搜索Python本地部署Azure学习视频检索MCP服务器技术查询

安装与配置

stdio · 本地进程 API Key
客户端在本机拉起子进程,数据不出本机
pip install -r requirements.txt

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 5 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
联网搜索取证

让模型查最新资料并给出出处。

资料聚合

把一个主题的网页、文档集中抓回来整理。

情报与竞品检索

按关键词持续检索行业动态和竞品信息。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 5 个工具,职责相对集中,接入后不容易误操作。
  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好API Key对应的凭据,并按最小权限配置。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在搜索检索场景里让模型直接调用外部能力的人。
  • 已经在用 Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Yt Azure MCP当前 5 stdio · 本地进程 本地部署 有 2026-05-17
Brave Search 433812ff 2 未标注 未标注 无 2026-05-17
Sequentialthinking 1 SSE · 服务端推送 远程部署 有 2026-05-18
Baidu Netdisk 未标注 未标注 未标注 无 2026-05-17
ragflow 未标注 stdio · 本地进程 本地部署 有 2026-04-11
mindsdb (430e18) 未标注 未标注 未标注 有 2026-05-17

服务器档案

搜索检索
字段来自项目仓库与公开索引,中文说明由本站标注
提供方danielsegan上游标注的维护方 danielsegan
分类搜索检索本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式API Key远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

7.3 KB
来自项目仓库与上游目录的原文,未做删改

John Savill Azure YouTube Search MCP Server

An MCP (Model Context Protocol) server that searches John Savill's YouTube channel for relevant Azure-related videos based on questions.

This server uses Streamable HTTP transport and is designed for deployment to Azure App Service.

Features

  • Search Azure Videos: Search John Savill's YouTube channel for videos relevant to Azure questions
  • Get Channel Info: Retrieve information about John Savill's YouTube channel
  • Relevant Results: Uses YouTube's relevance algorithm to find the most appropriate videos

Prerequisites

  1. Python 3.8+ installed
  2. YouTube Data API v3 Key: You need to obtain a YouTube Data API key from Google Cloud Console

Getting a YouTube Data API Key

Follow these detailed steps to get your YouTube API key:

  1. Go to Google Cloud Console
    - Visit https://console.cloud.google.com/
    - Sign in with your Google account

  2. Create or Select a Project
    - Click the project dropdown at the top of the page
    - Click "New Project"
    - Enter a project name (e.g., "YouTube MCP Server")
    - Click "Create"
    - Wait for the project to be created, then select it from the dropdown

  3. Enable YouTube Data API v3
    - In the left sidebar, go to "APIs & Services" > "Library"
    - Search for "YouTube Data API v3"
    - Click on "YouTube Data API v3" from the results
    - Click the "Enable" button
    - Wait for the API to be enabled (this may take a minute)

  4. Create API Credentials
    - Go to "APIs & Services" > "Credentials" in the left sidebar
    - Click "+ CREATE CREDENTIALS" at the top
    - Select "API key" from the dropdown
    - Your API key will be generated and displayed in a popup
    - Important: Copy the API key immediately (you can't see it again later)
    - Click "Close"

  5. Optional: Restrict the API Key (Recommended for Security)
    - Click on your newly created API key in the credentials list
    - Under "API restrictions", select "Restrict key"
    - Check "YouTube Data API v3"
    - Under "Application restrictions", you can optionally restrict by IP or HTTP referrer
    - Click "Save"

  6. Set the API Key
    - Copy your API key
    - Set it as an environment variable:```bash
    export YOUTUBE_API_KEY="your-api-key-here"

- Or add it to your shell profile (`~/.zshrc` or `~/.bashrc`) to make it persistent:```bash
echo 'export YOUTUBE_API_KEY="your-api-key-here"' >> ~/.zshrc
source ~/.zshrc

Note: The free tier allows 10,000 units per day. Each search request costs 100 units, so you can make approximately 100 searches per day for free.

Installation

  1. Clone or navigate to this directory:```bash
    cd YTAzureMCP

2. Install dependencies:```bash
pip install -r requirements.txt
  1. Set your YouTube API key as an environment variable:```bash
    export YOUTUBE_API_KEY="your-api-key-here"

Or on Windows:```cmd
set YOUTUBE_API_KEY=your-api-key-here

Running the Server

Local Development```bash

Activate virtual environment

source venv/bin/activate

Run the server

python server.py


The server will start on `http://localhost:8001/mcp` by default.

### Azure App Service Deployment

This server is designed for deployment to Azure App Service. See azure-mcp-deploy.md for detailed deployment instructions.

**Quick deploy:**
1. Set startup command: `bash startup.sh`
2. Set environment variable: `YOUTUBE_API_KEY=your-key`
3. Deploy code from GitHub or ZIP

## MCP Client Configuration

This server uses **Streamable HTTP transport** and must be accessed via HTTP/HTTPS URL.

### For VSCode/Cursor

Configure your MCP client with the server URL:

**Local:**```json
{
"mcpServers": {
"john-savill-azure-youtube": {
"url": "http://127.0.0.1:8001/mcp"
}
}
}

Azure (after deployment):```json
{
"mcpServers": {
"john-savill-azure-youtube": {
"url": "https://your-app.azurewebsites.net/mcp"
}
}
}


**Note:** The server must be running before the client connects. For local development, start the server first.

## Available Tools

### `search_azure_videos`

Searches John Savill's YouTube channel for videos relevant to a question or topic.

**Parameters:**
- `question` (string, required): The question or topic to search for (can be any topic, not just Azure)
- `max_results` (integer, optional): Maximum number of videos to return (default: 5, max: 50)
- `search_transcripts` (boolean, optional): If True, also search video transcripts (default: False)

**Returns:**
- JSON object with video information including title, URL, description, view count, duration, and optionally transcript matches

**Example:**```python
search_azure_videos(
question="How to set up Azure Functions",
max_results=5,
search_transcripts=True
)

get_channel_info

Retrieves information about John Savill's YouTube channel.

Returns:
- JSON object with channel information including name, subscriber count, video count, and description

get_latest_videos

Get the most recently published videos from John Savill's channel.

Parameters:
- count (integer, optional): Number of latest videos to return (default: 10, max: 50)

Returns:
- JSON object with the most recent videos including full details and thumbnails

Example:```python
get_latest_videos(count=10)


### `search_with_filters`

Search with advanced filtering options.

**Parameters:**
- `question` (string, required): The question or topic to search for
- `max_results` (integer, optional): Maximum number of videos (default: 5, max: 50)
- `min_views` (integer, optional): Minimum view count filter
- `published_after` (string, optional): Filter videos published after this date (ISO 8601 format, e.g., "2024-01-01T00:00:00Z")
- `published_before` (string, optional): Filter videos published before this date (ISO 8601 format)
- `max_duration_minutes` (integer, optional): Maximum video duration in minutes
- `sort_by` (string, optional): Sort order - "relevance", "date", "viewCount", "rating" (default: "relevance")

**Returns:**
- JSON object with filtered video results

**Example:**```python
search_with_filters(
question="Azure Functions",
min_views=10000,
published_after="2024-01-01T00:00:00Z",
max_duration_minutes=30,
sort_by="viewCount"
)

search_playlist

Search for videos within a specific playlist.

Parameters:
- playlist_name (string, required): Name or partial name of the playlist (e.g., "Azure Master Class", "Certification Cram")
- query (string, required): Search query within the playlist
- max_results (integer, optional): Maximum number of videos (default: 10, max: 50)

Returns:
- JSON object with videos from the playlist matching the query

Common Playlists:
- "Azure Master Class"
- "Certification Cram Videos"
- "DevOps Master Class"
- "PowerShell Master Class"
- "Weekly Azure Update"
- "Mentoring Content"

Example:python search_playlist( playlist_name="Azure Master Class", query="Functions", max_results=10 )

Example Usage

Once configured, you can ask questions like:
- "How do I deploy an Azure Function App?"
- "What is Azure Kubernetes Service?"
- "How to configure Azure AD B2C?"
- "Azure cost optimization strategies"

The server will search John Savill's channel and return relevant video results.

Notes

  • The server searches specifically on John Savill's channel (channel ID: UCpIn7ox7j7bH_OFj7tYouOQ)
  • Results are ordered by relevance
  • The YouTube Data API has quota limits - be mindful of your API usage
  • Free tier allows 10,000 units per day (1 search = 100 units)

License

MIT

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Yt Azure MCP 怎么安装?

在客户端按下面的安装命令接入:pip install -r requirements.txt。装完在客户端配置里引用同一个包或端点。

Yt Azure MCP 怎么在 Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Yt Azure MCP 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Yt Azure MCP 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

Yt Azure MCP 支持哪些客户端?

资料标注支持 Cursor;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Yt Azure MCP 能提供哪些能力?

资料显示约 5 个工具;能力标签包括 Python、Cursor、搜索。具体工具清单以官方文档为准。

Yt Azure MCP 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Yt Azure MCP 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。