# EdgeTag AI

## Talk to your data with AI

EdgeTag MCP brings your first-party data infrastructure directly into AI assistants. Instead of switching between dashboards, writing SQL manually, or digging through logs, you can ask questions in plain language and get instant answers about your domains, events, users, consent, and more.

### What is MCP?

MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools and data sources. Think of it as a universal plug that gives your AI assistant access to live data from services you already use.

### Why we built it

As marketers and engineers use AI assistants daily, we saw an opportunity to make EdgeTag data accessible where people already work. Instead of context-switching to the EdgeTag dashboard for every question, you can now:

* **Ask about traffic** - "How many purchases did we have last week?" or "What's our PageView trend today?"
* **Debug issues in real-time** - Stream live server logs and inspect events as they flow through EdgeTag
* **Query user data** - Look up specific users in the ID Graph without writing SQL
* **Analyze security** - Understand bot traffic and WAF attack patterns
* **Check channel health** - Get Meta EMQ scores and error breakdowns per channel

### How it works

EdgeTag exposes a remote MCP server at `https://mcp.edgetag.io` that connects to your AI assistant via Server-Sent Events (SSE). When you first connect, you authenticate with your EdgeTag account through OAuth. After that, your AI assistant has access to 22 tools that cover everything from domain management to real-time debugging.

The entire flow takes less than 2 minutes to set up and works with any MCP-compatible AI application.

### Getting started

{% content-ref url="/pages/ch0p9TRAPgIlTnvoSeRz" %}
[Installation](/mcp/installation/overview.md)
{% endcontent-ref %}

{% content-ref url="/pages/LKtW6eNlYfUObGNLwRJn" %}
[Tools](/mcp/tools/overview.md)
{% endcontent-ref %}

{% content-ref url="/pages/4zKYkx4wQTDYReBrCw5z" %}
[Skills](/mcp/skills/overview.md)
{% endcontent-ref %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.edgetag.io/mcp/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.