Android Proxy MCP
A

Android Proxy MCP

Android packet capturing MCP service, capturing HTTP/HTTPS traffic through a proxy and supporting AI assistant query and analysis of network requests
2.5 points
6.1K

What is Android Proxy MCP?

Android Proxy MCP is an intelligent packet capturing tool that allows AI assistants (such as Claude) to access and analyze the network traffic of Android devices through the Model Context Protocol (MCP). You only need to set up a proxy on your phone, and then you can use natural language to ask the AI to analyze network requests, such as finding specific interfaces, analyzing API parameters, or searching response content.

How to use Android Proxy MCP?

The usage is divided into four main steps: 1) Start the proxy service on your computer; 2) Configure the Wi-Fi proxy on your phone; 3) Install the CA certificate to capture HTTPS traffic; 4) Query and analyze the traffic through natural language in Claude. The whole process does not require writing complex filtering rules, and the AI will understand your needs and return relevant results.

Applicable scenarios

Suitable for mobile app developers, security researchers, product managers, or anyone who needs to analyze the network behavior of Android apps. Common scenarios include: API interface analysis, network performance debugging, data leakage detection, competitor analysis, automated testing, etc.

Main features

Intelligent traffic capture
Automatically capture HTTP/HTTPS traffic, supporting filtering and screening requests by domain name, status code, resource type, and other methods.
AI-driven intelligent search
Search request and response content through natural language, supporting multi-dimensional searches such as URL, request headers, request body, response headers, and response body.
Large response fragment reading
Intelligently handle large response bodies, supporting fragment reading to avoid the problem of MCP message size limitation.
HTTPS decryption support
Support HTTPS traffic decryption, providing detailed certificate installation guides and SSL Pinning bypass solutions.
SQLite data storage
Use the SQLite database to store traffic data, ensuring data persistence and fast querying.
Natural language interaction
Interact with the AI assistant completely through natural language, without the need to learn complex command-line parameters or filtering syntax.
Advantages
No technical background required: Complete complex traffic analysis tasks through natural language
Intelligent filtering: The AI understands your intentions and automatically applies appropriate filtering conditions
Integrated solution: A complete workflow from proxy setup to data analysis
Cross-platform support: Support multiple Android versions and devices
Open source and free: Based on the MIT license, can be freely used and modified
Limitations
Root permission required: Some advanced functions (such as system certificate installation) require a rooted device
HTTPS limitation: User certificates are not trusted by apps by default on Android 7+
SSL Pinning: Some apps use certificate pinning, requiring additional tools to bypass
Network requirement: The phone and computer must be on the same Wi-Fi network
Real-time performance: Non-real-time analysis, requiring traffic to be captured first and then queried

How to use

Environment preparation
Ensure that Python 3.11+ and the uv package manager are installed on your computer. Clone the project and install the dependencies.
Configure Claude Desktop
Edit the Claude Desktop configuration file and add the MCP server configuration.
Start the proxy service
Run the startup script in the terminal to obtain the proxy server address and port.
Configure the phone proxy
Configure a manual proxy in the phone's Wi-Fi settings, using the IP and port displayed by the startup script.
Install the CA certificate
Access http://mitm.it in the phone browser to download and install the CA certificate to support HTTPS traffic decryption.
Start using
Restart Claude Desktop and start querying and analyzing network traffic using natural language.

Usage examples

API interface analysis
Analyze the API interface structure and parameters of an app to understand its data interaction method.
Error troubleshooting
Find network errors or failed requests in the app to help debug problems.
Data search
Search for specific data content, such as user information and keywords, in a large number of network requests.
Performance analysis
Analyze the time-consuming and performance of network requests to find bottlenecks.
Security audit
Check if there is insecure network communication in the app, such as plaintext transmission of sensitive data.

Frequently Asked Questions

What should I do if I can't access the Internet after configuring the proxy on my phone?
I can capture HTTP traffic but not HTTPS traffic. What should I do?
I installed the certificate, but some apps still can't capture HTTPS traffic. What should I do?
How to bypass SSL Pinning (certificate pinning)?
The response is too large, and Claude cannot display the full content. What should I do?
Will packet capturing affect the phone's network speed?
How to stop packet capturing?
Does it support iOS devices?

Related resources

Project GitHub repository
Source code, issue feedback, and contribution guidelines
MCP official documentation
Official documentation and specifications of the Model Context Protocol
mitmproxy documentation
Detailed documentation of the underlying proxy tool mitmproxy
Magisk project
Android Root solution for advanced features
LSPosed framework
Android module framework for bypassing SSL Pinning
Video tutorial
Video tutorial on installing and using Android Proxy MCP

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "android-proxy": {
      "command": "uv",
      "args": ["--directory", "/path/to/android-proxy-mcp", "run", "android-proxy-mcp"]
    }
  }
}
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
6.3K
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
5.8K
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
5.2K
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
5.4K
4 points
P
Paperbanana
Python
7.8K
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
6.5K
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
6.7K
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
6.5K
5 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
21.6K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
73.1K
4.3 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
35.8K
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
26.0K
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
64.1K
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#
32.6K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.1K
4.5 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
48.7K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase