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

# Overview

What the Mozark MCP server does.

The **Mozark MCP Server** connects AI assistants such as Claude, Cursor, VS Code Copilot and Codex to your Mozark workspace using the open [Model Context Protocol (MCP)](https://modelcontextprotocol.io/).

Once connected, you can talk to your assistant in plain English and it will use Mozark on your behalf:

> *"Generate negative functional test cases for the checkout flow and save them to the Payments folder."*
>
> *"Run TR-12 on a free Pixel 7 with screen recording on and record step results."*
>
> *"Find duplicate test cases in this project and show me what you'd merge."*

{% hint style="info" %}
**New to MCP?** Think of it as a universal plug. Your AI assistant is the client, Mozark is the server, and the "tools" are the actions the assistant is allowed to take — list devices, create a test case, run a keyword on a phone, and so on. You never call tools yourself; you just describe what you want.
{% endhint %}

## What you can do

| Area                               | What the assistant can do                                                                                                                                      |
| ---------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Test Case Management (TCM)**     | Create, search, update and organise test cases, folders, requirements, test plans, test runs and bugs.                                                         |
| **AI test generation**             | Generate functional, edge-case or automation test cases from your app screenshots and requirement documents, then save them with AI-provenance tags.           |
| **Knowledge base**                 | Upload screenshots, PRDs, BRDs and user stories so generated tests are grounded in your real app.                                                              |
| **Real-device execution (Optics)** | Execute a test case step-by-step on a real Android or iOS device, verify each step visually, record results into a test run and export a reusable YAML script. |
| **Device automation (Appium)**     | Start raw Appium sessions on Mozark cloud devices — install your APK/IPA, find and tap elements, take screenshots, pull logs and HAR files.                    |
| **Admin Control Panel (ACP)**      | Look up your organisations, projects, apps, users, roles, plan entitlements and usage.                                                                         |

## Navigate the documentation

* **Getting started** — connect your client, sign in, and set your working context in five minutes.
* **Guides** — task-based walkthroughs for the most common workflows.
* **Reference** — every tool grouped by category, with example prompts.
* **Troubleshooting & FAQ** — common errors and how to fix them.

{% content-ref url="/spaces/sKHRrJ2t9qZCDuT5wRkG/pages/00ccc7bc83adffba3acdfbb761b159ccffeb0dbe" %}
[Getting started](/mcp/mozark-mcp-docs/getting-started.md)
{% endcontent-ref %}


---

# 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.mozark.ai/mcp/mozark-mcp-docs/overview.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.