Which integrations are available for this server?

Provides screen analysis capabilities for Android devices via ADB, enabling AI agents to ask questions about the screen content and receive coordinates or instructions.

How do I use autoglm-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. 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.

AutoGLM MCP Server

Android screen analysis capabilities via MCP protocol.

Installation

Option 1: Using uvx (Recommended)

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"
      }
    }
  }
}

Option 2: pip install

pip install autoglm-mcp

Then 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"
      }
    }
  }
}

Environment Variables

Variable	Description	Default
`AUTOGLM_APIKEY`	API key (required)	-
`AUTOGLM_BASE_URL`	API endpoint	`https://api.z.ai/api/paas/v4`
`AUTOGLM_MODEL`	Model name	`autoglm-phone-multilingual`

Usage

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?"

Local Development & Debugging

Prerequisites

Python >= 3.10
Node.js >= 18 (for MCP Inspector)
ADB installed and phone connected (adb devices shows your device)

Install from Source

cd mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

MCP Inspector (Recommended)

MCP 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.server

Then 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

Use local mcp server

"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 installed

A

license - permissive license

-

quality - not tested

C

maintenance

How are these scores calculated?

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

autoglm-mcp