Provides screen analysis capabilities for Android devices via ADB, enabling AI agents to ask questions about the screen content and receive coordinates or instructions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@autoglm-mcp What is on my phone screen right now?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Android screen analysis capabilities via MCP protocol.
No manual installation required. Just add to AI agent MCP config:
{
"mcpServers": {
"autoglm-mcp": {
"command": "uvx",
"args": ["autoglm-mcp"],
"env": {
"AUTOGLM_BASE_URL": "https://api.z.ai/api/paas/v4",
"AUTOGLM_MODEL": "autoglm-phone-multilingual",
"AUTOGLM_APIKEY": "your-api-key-here"
}
}
}
}pip install autoglm-mcpThen configure AI agent MCP:
{
"mcpServers": {
"autoglm-mcp": {
"command": "autoglm-mcp",
"env": {
"AUTOGLM_BASE_URL": "https://api.z.ai/api/paas/v4",
"AUTOGLM_MODEL": "autoglm-phone-multilingual",
"AUTOGLM_APIKEY": "your-api-key-here"
}
}
}
}Related MCP server: autoglm-mcp-server
Variable | Description | Default |
| API key (required) | - |
| API endpoint |
|
| Model name |
|
Ensure your phone is connected via ADB, then use the aiAsk tool in AI agent:
"What are the coordinates to click the search button?"
"How do I open Settings?"
Python >= 3.10
Node.js >= 18 (for MCP Inspector)
ADB installed and phone connected (adb devices shows your device)
cd mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtMCP Inspector is the official visual debugging tool for MCP servers — like Postman for MCP.
npx @modelcontextprotocol/inspector \
-e AUTOGLM_APIKEY="your-api-key-here" \
-e AUTOGLM_BASE_URL="https://api.z.ai/api/paas/v4" \
-e AUTOGLM_MODEL="autoglm-phone-multilingual" \
-- \
/path/to/file/mcp/.venv/bin/python -m autoglm_mcp.serverThen open http://localhost:6274 in your browser:
Click Connect to connect to the server
Switch to the Tools tab — you should see the aiAsk tool
Enter a question (e.g. "What is on the screen?") and click Run Tool
Inspect the JSON-RPC request/response in the left panel
"autoglm-mcp": {
"command": "/path/to/file/mcp/.venv/bin/python",
"args": [
"-m",
"autoglm_mcp.server"
],
"env": {
"AUTOGLM_BASE_URL": "https://api.z.ai/api/paas/v4",
"AUTOGLM_MODEL": "autoglm-phone-multilingual",
"AUTOGLM_APIKEY": "xxx"
}
}This server cannot be deployed
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
Disposable cloud Android emulators for coding agents: run an APK or PR build, tap, type, screenshot.
Melaya is a remote MCP server. It gives an assistant hands on your own Android phone and browser: it reads the screen through the accessibility tree, then taps, types and navigates inside the apps and sites you allow-list, with no per-app API. It also builds, schedules and runs agent pipelines across 6k+ connected tools. OAuth 2.1, nothing to install.
Drive real devices from your AI Coding tool. Embed a client SDK (Unity, Godot, Flutter, iOS/macOS, Android, React Native, Web) in your app, then capture screenshots, traverse the UI tree, inject taps and key events, and run automated test tasks on the physical device over a secure relay.
