# Vitrus analytics

Connects privacy-first web and mobile analytics to your AI agent over MCP. Lets you inspect traffic, churn and revenue alongside the exact SQL query behind each figure.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 4
- Author: Vitrus-Dev
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Vitrus-Dev/vitrus
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/vitrus-analytics

## What it does

The server links your development agent with metrics gathered from web, iOS, and Android applications. Vitrus tracks visits, subscription plans, and churn without using cookies. Device SDKs hash user identifiers with SHA-256 before transmitting data. Values shaped like email addresses or phone numbers are dropped automatically on both client and server.

Every metric exposes the underlying SQL statement, its execution parameters, and the time window. Vitrus validates model summaries against this database evidence. If an AI summary introduces figures missing from the raw query output, the system drops the statement. MCP tools like `get_portfolio` and `get_lifecycle` provide structured numbers directly to the model.

Self-hosting requires Bun 1.3 or newer alongside SQLite. If you prefer zero local setup, the hosted cloud endpoint at `https://app.vitrus.dev/mcp` connects immediately over HTTP.

## Requirements
- Remote server: `https://app.vitrus.dev/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http analytics https://app.vitrus.dev/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add vitrus-analytics --url https://app.vitrus.dev/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "vitrus-analytics": {
            "url": "https://app.vitrus.dev/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "vitrus-analytics": {
            "type": "http",
            "url": "https://app.vitrus.dev/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http vitrus-analytics https://app.vitrus.dev/mcp
```

## When to use it
- inspect SQL queries powering specific dashboard figures
- track retention and user churn across multiple applications
- prevent hallucinated metrics in automated analytical summaries
- review subscription tiers and active user counts in chat

## Example prompts
- Check get_portfolio and show which app lost the most users this week.
- Run get_lifecycle to see how many people returned after sign-up.
- Inspect the SQL query behind our latest unique visitor count.

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40459
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27844
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49863

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md