> For the complete documentation index, see [llms.txt](https://docs.hackle.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.hackle.io/en/ai/model-context-protocol.md).

# MCP Integration

Hackle MCP (*Model Context Protocol*) enables AI clients such as Claude and ChatGPT to query and analyze your data using natural language.

The experiment, message, and analytics data you used to check by clicking through the dashboard can now be asked, interpreted, and even visualized through a conversation with AI.

{% hint style="success" %}
With Hackle MCP, you can work through tasks like the examples below together with AI.

* **Interpreting experiment results**: *"Summarize the results of the A/B test I started last week."*
* **Measuring message performance**: *"Compare the conversion rates of recent push campaigns."*
* **Analyzing user trends**: *"Show me the DAU trend over the last 30 days along with the 7-day retention."*
* **Funnel analysis**: *"Draw a chart of the step-by-step drop-off rate from sign-up to first payment."*
* **Automating operations**: *"Among the experiments that ended today, tell me only the ones that are statistically significant."*
  {% endhint %}

## How It Works

```mermaid
flowchart LR
    client["AI Client"]
    server["Hackle MCP Server"]
    workspace["Hackle Workspace"]

    client --> server --> workspace
```

1. When you ask a question in natural language to an AI client,
2. the request goes through the MCP server running on Hackle's infrastructure,
3. which accesses your Hackle Workspace to query the data.

{% hint style="success" %}
The Hackle MCP server runs on Hackle's infrastructure, so no separate installation is required.
{% endhint %}

## Getting Started

You can request an API key from the **MCP Integration** menu in the [Hackle Dashboard](https://dashboard.hackle.io/).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.hackle.io/en/ai/model-context-protocol.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.