How do I install espresso-mcp?
Ensure Python 3.x and uv are installed, then run `uvx espresso-mcp`. Optionally install via `uv tool install espresso-mcp`.
@vs4vijay
基本信息
An MCP Server for the Espresso Android Test Framework, crafted to improve testing capabilities and optimize development workflows.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"espresso-mcp": {
"command": "uvx",
"args": [
"espresso-mcp"
]
}
}
}List all available Android Virtual Devices (AVDs).
List all running Android Emulators.
Start an Android Emulator by name.
Kill a specific Android Emulator.
Dump the UI hierarchy of the connected Android device.
Open a URI on the connected Android device.
List all installed apps on the connected Android device.
Install an APK on the connected Android device.
Start a specific app on the connected Android device.
Stop a specific app on the connected Android device.
Uninstall an app from the connected Android device.
Clear app data for a specific app on the connected Android device.
Take a screenshot of the connected Android device.
Record the screen of the connected Android device for a specified duration.
Simulate a button press on the connected Android device.
Type text on the connected Android device.
Clear all text and type new text on the connected Android device.
Replace text by clearing current text and typing new text on the connected Android device.
Simulate a tap on the connected Android device at specific coordinates.
Perform a swipe gesture in a specific direction on the connected Android device.
Dump the current activity name of the connected Android device.
espresso-mcp is an MCP (Model Context Protocol) server for the Espresso Android Test Framework. It provides tools to interact with Android emulators and devices, enabling UI automation, emulator management, and testing workflows. It is designed for Android developers and testers who want to integrate testing capabilities into AI-assisted development environments.
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.
Ensure Python 3.x and uv are installed, then run `uvx espresso-mcp`. Optionally install via `uv tool install espresso-mcp`.
It supports both stdio (default) and SSE (`--sse` flag) transports.
Python 3.x and the `uv` package manager (installable via `pip install uv`). An Android emulator or device must be connected and accessible via ADB.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Agent-Native Terminal

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url
Unipile MCP server: LinkedIn MCP (Sales Navigator, Recruiter), WhatsApp, Instagram, Telegram and email MCP for coding agents. Build your LinkedIn, WhatsApp and email API integration from Cursor, Claude Code, Codex.
评论