YouTube Analytics
Track your YouTube channel performance — views, watch time, subscriber growth, and per-video engagement. Powered by Boring.
Security & Data Handling
- - MCP link is a credential: Your MCP Server URL (
https://boring.aiagent-me.com/mcp/t/xxxxx...) contains an embedded authentication token. Treat it like a password — do not share it publicly. - Token scope: The embedded token is read-only for analytics. It can only fetch performance metrics and account metadata. It cannot publish, delete, or modify any content on your social media accounts.
- Token storage: The token is stored server-side in Boring's database (MongoDB on DigitalOcean). It is never written to your local filesystem. You can regenerate or revoke it anytime at boring.aiagent-me.com/settings.
- Data flow: Analytics queries are sent from Boring's server (Google Cloud, us-central1) to the platform's API on your behalf. Only performance metrics are retrieved — no content is uploaded or modified.
- No local credentials: No local API keys, environment variables, or secrets are needed. All auth is embedded in the MCP link.
- Third-party service: This skill relies on Boring, an open-source social media management tool. Source code: github.com/snoopyrain.
Prerequisites
- 1. Sign up at boring.aiagent-me.com with Google
- Connect YouTube — select the target channel during OAuth
- Get your MCP link: Go to Settings → copy your MCP Server URL (contains your auth token — treat it like a password)
- Add to Claude: Paste the MCP link as a Connector — no install, no API key needed
Available Tools
| Tool | Data Source | Best For |
|---|
| INLINECODE1 | Real-time platform API | Channel-level overview (views, watch time, subscribers) |
| INLINECODE2 |
Real-time platform API | Per-video metrics (views, likes, comments, shares, watch time) |
|
boring_get_posts_performance | Daily snapshots (collected at 2 AM) | Historical video performance over date ranges |
|
boring_get_publish_history | Boring database | Publishing history and status tracking |
Workflow
Step 1: List Accounts
Call boring_list_accounts and filter for youtube platform.
Step 2: Determine What the User Wants
| User Request | Tool to Use |
|---|
| "How is my YouTube doing?" | INLINECODE7 |
| "Show my best videos" |
boring_get_video_analytics |
| "YouTube performance this month" |
boring_get_posts_performance |
| "What did I upload recently?" |
boring_get_publish_history |
Step 3: Fetch Data
Channel-Level Performance
CODEBLOCK0
Per-Video Analytics (Real-Time)
CODEBLOCK1
Historical Video Performance (Snapshots)
CODEBLOCK2
Step 4: Present Results
Format the data clearly:
- - Channel overview: Show views, watch time, subscriber changes in a summary table
- Video analytics: Rank videos by views or engagement, highlight top performers
- Historical: Show trends over time, compare Shorts vs long-form
YouTube Metrics
| Metric | Description |
|---|
| INLINECODE11 | Total video views |
| INLINECODE12 |
Video likes |
|
comments | Video comments |
|
shares | Video shares |
|
estimatedMinutesWatched | Total watch time in minutes |
|
averageViewDuration | Average view duration |
|
subscribersGained | New subscribers gained |
|
subscribersLost | Subscribers lost |
Error Handling
| Error | Solution |
|---|
| INLINECODE19 | MCP link may be invalid — regenerate it at boring.aiagent-me.com Settings |
| INLINECODE20 |
Run
boring_list_accounts to get valid IDs |
|
TokenExpired | Reconnect account at boring.aiagent-me.com |
| No data returned | Account may be newly connected — data collection runs daily at 2 AM |
Documentation
Full API docs: boring-doc.aiagent-me.com
YouTube 数据分析
追踪您的YouTube频道表现——观看次数、观看时长、订阅者增长以及每个视频的互动情况。由 Boring 提供技术支持。
安全与数据处理
- - MCP链接即凭证:您的MCP服务器URL(https://boring.aiagent-me.com/mcp/t/xxxxx...)包含嵌入式身份验证令牌。请像对待密码一样对待它——不要公开分享。
- 令牌范围:嵌入式令牌对分析功能为只读。它只能获取性能指标和账户元数据。无法在您的社交媒体账户上发布、删除或修改任何内容。
- 令牌存储:令牌存储在Boring的数据库(DigitalOcean上的MongoDB)服务器端。它永远不会写入您的本地文件系统。您可以随时在 boring.aiagent-me.com/settings 重新生成或撤销它。
- 数据流:分析查询从Boring的服务器(Google Cloud,us-central1)代表您发送到平台的API。仅检索性能指标——不会上传或修改任何内容。
- 无本地凭证:无需本地API密钥、环境变量或密钥。所有身份验证都嵌入在MCP链接中。
- 第三方服务:此技能依赖于 Boring,一个开源社交媒体管理工具。源代码:github.com/snoopyrain。
前提条件
- 1. 注册 boring.aiagent-me.com(使用Google账号)
- 连接YouTube——在OAuth期间选择目标频道
- 获取您的MCP链接:前往设置 → 复制您的MCP服务器URL(包含您的身份验证令牌——请像对待密码一样对待它)
- 添加到Claude:将MCP链接粘贴为连接器——无需安装,无需API密钥
可用工具
| 工具 | 数据源 | 最佳用途 |
|---|
| boringgetperformance | 实时平台API | 频道级别概览(观看次数、观看时长、订阅者) |
| boringgetvideo_analytics |
实时平台API | 每个视频的指标(观看次数、点赞、评论、分享、观看时长) |
| boring
getposts_performance | 每日快照(凌晨2点收集) | 历史视频在日期范围内的表现 |
| boring
getpublish_history | Boring数据库 | 发布历史和状态追踪 |
工作流程
第1步:列出账户
调用 boringlistaccounts 并筛选 youtube 平台。
第2步:确定用户需求
| 用户请求 | 使用的工具 |
|---|
| 我的YouTube表现如何? | boringgetperformance |
| 展示我最好的视频 |
boring
getvideo_analytics |
| 本月YouTube表现 | boring
getposts_performance |
| 我最近上传了什么? | boring
getpublish_history |
第3步:获取数据
频道级别表现
boringgetperformance(
account_id=<账户ID>,
platform=youtube,
period=week // day、week 或 month
)
每个视频分析(实时)
boringgetvideo_analytics(
account_id=<账户ID>,
platform=youtube,
limit=20 // 最大100
)
历史视频表现(快照)
boringgetposts_performance(
account_id=<账户ID>,
since=2025-12-01,
until=2025-12-31,
limit=20
)
第4步:呈现结果
清晰格式化数据:
- - 频道概览:在摘要表中显示观看次数、观看时长、订阅者变化
- 视频分析:按观看次数或互动率对视频排序,突出表现最佳的
- 历史数据:显示随时间变化的趋势,比较Shorts与长视频
YouTube指标
视频点赞数 |
| comments | 视频评论数 |
| shares | 视频分享数 |
| estimatedMinutesWatched | 总观看时长(分钟) |
| averageViewDuration | 平均观看时长 |
| subscribersGained | 新增订阅者数 |
| subscribersLost | 流失订阅者数 |
错误处理
| 错误 | 解决方案 |
|---|
| InvalidApiKey | MCP链接可能无效——在boring.aiagent-me.com设置中重新生成 |
| InvalidAccountId |
运行 boring
listaccounts 获取有效ID |
| TokenExpired | 在boring.aiagent-me.com重新连接账户 |
| 未返回数据 | 账户可能刚连接——数据收集每天凌晨2点运行 |
文档
完整API文档:boring-doc.aiagent-me.com