vturb-mcp
MCP server for the vTurb Analytics API that exposes 15 tools to query real-time and historical video analytics directly from Claude, with built-in rate limiting and smart player detection.
README
vturb-mcp
MCP server for the vTurb Analytics API — exposes 15 tools to query real-time and historical video analytics directly from Claude.
Features
- 15 analytics tools covering sessions, events, engagement, clicks, conversions, traffic origin and more
- Built-in rate limiter — token bucket enforcing the Pro tier limit of 120 req/min (no 429 errors)
- Smart player detection —
find_active_playersauto-discovers which video is live today - Per-client
.envfiles — clean credential management across multiple accounts
Requirements
- Node.js ≥ 18
- A vTurb account with Analytics API access
- Your API token from app.vturb.com/settings/analytics-api
- Claude Code (CLI or VSCode extension)
Installation
1. Clone the repository
git clone https://github.com/hiperbold/vturb-mcp.git
cd vturb-mcp
npm install
npm run build
2. Create your .env file for each client
The MCP uses a per-client .env file so you can manage multiple vTurb accounts cleanly. Name the file after the client:
# Copy the example
cp .env.example .env.customer-name
# Edit and paste your token
# .env.customer-name
VTURB_API_TOKEN=your_token_here
The file format is simple — one variable per line:
VTURB_API_TOKEN=eyJ...
Security: Never commit
.env.*files. They are already in.gitignore.
3. Register the MCP server in Claude Code
Open ~/.claude/mcp.json (create it if it doesn't exist) and add:
{
"mcpServers": {
"vturb-mcp": {
"command": "node",
"args": ["/absolute/path/to/vturb-mcp/dist/index.js"],
"env": {
"VTURB_ENV_FILE": "/absolute/path/to/vturb-mcp/.env.customer-name"
}
}
}
}
Windows example:
{
"mcpServers": {
"vturb-mcp": {
"command": "node",
"args": ["F:\\local-mcps\\vturb-mcp\\dist\\index.js"],
"env": {
"VTURB_ENV_FILE": "F:\\local-mcps\\vturb-mcp\\.env.customer-name"
}
}
}
}
4. Restart Claude Code
The MCP server starts automatically on the next session. You'll see it listed in your available tools.
Switching between clients
To switch accounts, just update VTURB_ENV_FILE in mcp.json to point to a different .env file and restart Claude:
"VTURB_ENV_FILE": "F:\\local-mcps\\vturb-mcp\\.env.other-customer"
Available Tools
Discovery & Monitoring
| Tool | Description |
|---|---|
list_players |
Lists all players in the account with id, name, duration, and pitch_time. Supports optional filters by name and date range. |
find_active_players |
Smart tool. Lists all players, checks which ones have activity today, and returns only the active ones with their metadata. Use this first to discover the correct player_id. |
get_quota_usage |
Returns the current API quota status: queries used, remaining, and reset time. Use this to monitor consumption and avoid hitting the 120 req/min limit. |
get_live_users |
Returns the number of users currently watching, broken down by domain. Configurable time window (1–720 minutes). |
Session Analytics
| Tool | Description |
|---|---|
get_session_stats |
Main analytics dashboard for a player: total views, plays, unique sessions/devices, engagement rate, clicks, conversions, and revenue in BRL/USD/EUR. |
get_session_stats_by_day |
Same metrics as get_session_stats but broken down day by day. Ideal for historical trend analysis. |
Events
| Tool | Description |
|---|---|
get_events_total |
Returns totals for started, finished, and/or viewed events with unique session and device counts. |
get_events_by_day |
Same event totals broken down by day for trend analysis. |
Engagement & Retention
| Tool | Description |
|---|---|
get_user_engagement |
Returns the video retention curve: how many users are still watching at each second. Also returns average_watched_time and engagement_rate. |
get_user_engagement_by_day |
Returns the engagement rate per day over the selected period. |
Clicks
| Tool | Description |
|---|---|
get_clicks_timed |
Returns CTA click counts grouped by video second. Identifies the moment in the video that drives the most intent. |
get_clicks_by_day |
CTA click totals broken down by day. |
Conversions
| Tool | Description |
|---|---|
get_conversions_by_day |
Conversion totals grouped by day, with unique session and device counts. |
Traffic Origin
| Tool | Description |
|---|---|
get_traffic_origin_stats |
Breaks down session metrics by traffic source. Supports utm_source, utm_medium, utm_campaign, utm_content, utm_term, src, sck. |
Dashboard Summary
| Tool | Description |
|---|---|
get_headlines_stats |
Returns a pre-computed summary (views, plays, engagement rate, clicks, and conversion rate) — the same numbers shown in the vTurb dashboard header. |
Typical Workflow
1. find_active_players → discover which player_id is in use today
2. get_session_stats → get the main KPIs for a date range
3. get_user_engagement → inspect the retention curve
4. get_clicks_timed → find when viewers click the CTA
5. get_conversions_by_day → track conversion trends
6. get_traffic_origin_stats → compare traffic sources
Rate Limiting
The client uses a token bucket algorithm configured for the Pro tier:
- Limit: 120 requests per minute
- Refill rate: 2 tokens per second
- Behavior: requests wait automatically if the bucket is empty — no errors thrown, no retries needed
Use get_quota_usage to check live consumption from vTurb's side.
Project Structure
vturb-mcp/
src/
env.ts — loads .env.* file at startup (via VTURB_ENV_FILE)
client.ts — rate-limited HTTP client (token bucket, 120 req/min)
index.ts — MCP server, registers all 15 tools
tools/ — one file per tool
list-players.ts
find-active-players.ts
get-quota-usage.ts
get-session-stats.ts
get-session-stats-by-day.ts
get-events-total.ts
get-events-by-day.ts
get-user-engagement.ts
get-user-engagement-by-day.ts
get-clicks-timed.ts
get-clicks-by-day.ts
get-conversions-by-day.ts
get-live-users.ts
get-headlines-stats.ts
get-traffic-origin-stats.ts
dist/ — compiled output (run npm run build)
.env.example — template for creating client-specific env files
API Reference
- vTurb Analytics API Docs
- Base URL:
https://analytics.vturb.net - Auth headers:
X-Api-Token+X-Api-Version: v1
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。