AutomateAI exposes its testing agents over the Model Context Protocol (MCP), so the AI tooling your team already uses can trigger runs and read results directly — no separate dashboard required.
Connect locally for development, or remotely for CI/CD — both use the same set of tools.
Runs alongside your IDE for day-to-day development and debugging.
Claude Desktop Cursor Windsurf VS Code CopilotMulti-tenant hosted endpoint with API-key auth, built for pipelines.
CI/CD pipelines Custom agents Any MCP-speaking client| Tool | What it does |
|---|---|
| list_devices | Lists devices currently available on your connected farm. |
| run_test | Starts a test run for a given prompt or saved test against web, mobile, or chatbot. |
| get_test_result | Fetches the pass/fail verdict and step-by-step detail for a run. |
| get_device_screenshot | Pulls the current screen from a connected device mid-run. |
| farm_status | Reports which farm nodes and devices are online. |
| list_prompts | Returns saved test prompts available to run. |
| get_run_history | Returns past runs and their outcomes for a given test. |