AIBase
EN
Explore
Xiaozhi Autoglm MCP
X

Xiaozhi Autoglm MCP

An automated MCP service for Android devices built on Open - AutoGLM. It connects to the phone via ADB and invokes the visual model, and can access Xiaozhi AI for intelligent control.
Operating system automationDeveloper tools#Android Automation#MCP Service#Visual Control#ADB Manipulation.Python
2.5 points
9.4K
Open Site

Overview

Tools List

Content Details

Alternatives

What is the Xiaozhi AutoGLM MCP Service?

The Xiaozhi AutoGLM MCP Service is an intelligent Android device automation tool that allows you to control Android phones or tablets through natural language instructions. Based on advanced visual - language models, this service can understand screen content and perform corresponding operations, such as clicking, swiping, and entering text.

How to use the Xiaozhi AutoGLM MCP Service?

To use this service, you need to prepare an Android device (phone or emulator), connect it to your computer via USB, and complete the configuration of ADB and ADB Keyboard. After the configuration is completed, start the MCP service, and you can send instructions through Xiaozhi AI or a privately deployed Xiaozhi server to control the device.

Applicable Scenarios

This service is particularly suitable for scenarios that require automated operation of Android devices, such as automated testing, batch execution of repetitive tasks, remote device control, and providing auxiliary operations for visually impaired users.

Main Features

Automated Control of Android Devices
Through ADB connection, it can automatically execute basic operations such as clicking, swiping, and inputting on Android devices.
Driven by Visual - Language Models
Integrated with large visual - language models such as ChatGLM, it can understand the content of screenshots and convert natural language instructions into specific device operation steps.
MCP Protocol Access
Following the Model Context Protocol standard, it can easily access the Xiaozhi AI platform or a privately deployed Xiaozhi server for remote invocation.
Cross - Platform Support
It provides startup scripts for Linux/macOS and Windows systems, facilitating deployment and operation on different operating systems.
Advantages
Intelligent operation: No need to write complex scripts. You can control the device with natural language.
Easy to integrate: It can be quickly integrated into the existing AI assistant ecosystem through the standard MCP protocol.
Open - source and customizable: Built on the Open - AutoGLM open - source project, it can be secondarily developed according to requirements.
Supports real devices and emulators: It can be used for both real - device testing and emulator automation.
Limitations
Depends on external models: The visual understanding ability depends on third - party APIs such as ChatGLM, which may require payment and be affected by the network.
Many configuration steps: It requires installing ADB, configuring device developer options, installing an input method, etc., which has a certain threshold for beginners.
Only supports Android: Currently, it only supports devices running Android 7.0 or higher and does not support iOS or other systems.
Requires USB connection: Most operations require connecting the device via a USB data cable, which limits full wireless remote control.

How to Use

Environment Preparation: Install ADB Tools
Download the ADB toolkit from the Android developer official website, extract it to a local directory, and add this directory to the system's environment variable PATH so that you can directly use the adb command in the terminal.
Device Preparation: Enable Developer Options
On the Android device, go to 'Settings > About Phone', click on the 'Version Number' more than 7 times until the prompt 'You are now in developer mode' appears. Then return to the settings, enter the newly appeared 'Developer Options', and enable the 'USB Debugging' function.
Install ADB Keyboard Input Method
Install the ADB Keyboard APK file on the Android device. After installation, go to 'Settings > System > Languages and Input > Virtual Keyboard' and enable the 'ADB Keyboard' input method. This is the key to achieving automated text input.
Connect the Device and Verify
Connect the Android device to the computer using a USB data cable. Run the `adb devices` command in the computer terminal. If you see the device serial number and it shows 'device', it means the connection is successful.
Install Python Dependencies
Create a Python virtual environment and use pip to install all the required dependency libraries for the project.
Configure Service Parameters
Copy the configuration file template and modify the configuration file according to your Xiaozhi MCP service access point address and the API key of Zhipu AI (if using the ChatGLM model).
Start the MCP Service
Run the corresponding startup script according to your operating system to start the MCP service. After the service is started, it will wait for instructions from Xiaozhi AI.

Usage Cases

Case 1: Automated Sending of WeChat Messages
You want the assistant to help you send a WeChat message to a friend. You just need to tell the assistant 'Send a WeChat message to Li Si saying 'The project meeting is changed to 3 pm'.'
Case 2: Information Query and Recording
You want to query and record certain information (such as an express delivery number or verification code) displayed on the phone screen.
Case 3: Automated Application Operation Process
You need to perform fixed operations such as daily check - in and reward collection in a certain application every day.

Frequently Asked Questions

When connecting the device, the `adb devices` command does not show any devices. What should I do?
After installing ADB Keyboard, I cannot input Chinese or the input method does not work. What should I do?
The service prompts that the visual model API call fails or the balance is insufficient during operation. What should I do?
Can I control multiple Android devices simultaneously?
Does it support wireless connection (Wi - Fi debugging)?

Related Resources

Open - AutoGLM Open - Source Project
The Android automation open - source framework on which this project is based, containing more technical details and underlying implementations.
Android Platform Tools (ADB) Official Download
The official download page for the Android Debug Bridge (ADB) command - line tools.
ADB Keyboard Project Page
The source code and APK download for the Android input method application used to implement ADB text input.
Xiaozhi AI Official Website
The AI assistant platform that can access this MCP service.
Zhipu AI Open Platform
Provides API services for visual - language models such as ChatGLM, used for screen content understanding in this project.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
8.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.1K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.1K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.3K
4 points
P
Paperbanana
Python
8.1K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
8.3K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
8.9K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
9.5K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
36.3K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
76.9K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
22.5K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.9K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
67.8K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
36.5K
5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
52.7K
4.8 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
103.4K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2026AIBase