espresso-mcp
About
An MCP Server for the Espresso Android Test Framework, crafted to improve testing capabilities and optimize development workflows.
Details
- Author
- vs4vijay
- Downloads
- 402
- Categories
- Developer Tools, Automation, AI
Jump to
- List and manage Android Virtual Devices and emulators.
- Start/stop emulators and dump UI hierarchy.
- Install, uninstall, start, stop, and clear app data.
- Simulate taps, swipes, text input, and button presses.
- Take screenshots and record screen video.
- Retrieve static configuration and personalized greetings via resources.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
espresso-mcpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via uvx espresso-mcp (requires Python 3.x and uv). Run in stdio mode by default or in SSE mode with --sse. Configure in GitHub Copilot (.vscode/mcp.json), Claude Desktop (claude_desktop_config.json), or use directly with the OpenAI SDK by pointing to the SSE endpoint.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"espresso-mcp": {
"espresso-mcp": {
"command": "uvx",
"args": [
"espresso-mcp"
]
}
}
}
}
McpServers
{
"espresso-mcp": {
"command": "uvx",
"args": [
"espresso-mcp"
]
}
}
espresso-mcp
An MCP Server for the Espresso Android Test Framework, crafted to improve testing capabilities and optimize development workflows.
<a href="https://glama.ai/mcp/servers/@vs4vijay/espresso-mcp">
</a>
Installation
- Python 3.x
- uv: pip install uv
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.


