Vitrus analytics — Claude Code MCP server: how to install
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.
claude mcp add --transport http analytics https://app.vitrus.dev/mcpWhat Vitrus analytics 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.
What it helps with
- 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 for the agent
- 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.
How to install Vitrus analytics
Platform CLI: remote server
claude mcp add --transport http analytics https://app.vitrus.dev/mcpPlatform CLI: remote server
codex mcp add vitrus-analytics --url https://app.vitrus.dev/mcpConfig file
{
"mcpServers": {
"vitrus-analytics": {
"url": "https://app.vitrus.dev/mcp"
}
}
}Config file
{
"servers": {
"vitrus-analytics": {
"type": "http",
"url": "https://app.vitrus.dev/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http vitrus-analytics https://app.vitrus.dev/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Vitrus analytics
How do I install Vitrus analytics in Claude Code?
Run claude mcp add --transport http vitrus-analytics https://app.vitrus.dev/mcp in your terminal.
What does Vitrus analytics do?
It exposes website and application traffic, user lifecycle numbers, and revenue records to your AI assistant. Each reported metric includes the exact SQL query and filters used to produce it.
What is needed to run a self-hosted instance?
Running your own instance requires Bun 1.3 or higher. Alternatively, you can connect directly to the hosted endpoint at https://app.vitrus.dev without local dependencies.
