> ## Documentation Index
> Fetch the complete documentation index at: https://help.contentgrove.io/llms.txt
> Use this file to discover all available pages before exploring further.

# The contentgrove AI connector (MCP)

> What the contentgrove AI connector is: a read-only Model Context Protocol (MCP) connector that lets AI assistants read your contentgrove analytics.

The contentgrove connector lets an AI assistant read your analytics so you can ask questions in plain language instead of clicking through the dashboard. It's built on the Model Context Protocol (MCP), an open standard that AI clients like Claude and ChatGPT use to connect to external tools.

## How it works

You add contentgrove as a connector in your AI client and sign in with your contentgrove account. From then on, when you ask about your performance, the assistant reads the relevant data and answers.

## Read-only and tied to your account

<Note>
  The connection is read-only and scoped to your own contentgrove account. The assistant can read your analytics, but it can't create, change, or delete anything in contentgrove.
</Note>

## What it can read

* Analytics overview and period-over-period comparisons
* Per-video performance and monetization metrics
* Tracking link performance
* Geography and device breakdowns
* Your offers and their matching rules

## Next step

When you're ready, see [Connect your assistant](/ai-mcp/connect), then [What you can ask](/ai-mcp/what-you-can-ask) for examples.