mobile-security-mcp
Legitimate penetration testing toolkit — for use only on applications you are authorised to test.
An MCP (Model Context Protocol) server that effortlessly transforms any AI agent (Claude Code, Cline, Goose, OpenCode) into an elite Android security researcher by providing them direct access to the industry's most powerful reverse-engineering stack.
✨ Zero-Touch Automation
This MCP server features Zero-Touch automated configuration. It comes equipped with native Python downloaders that securely fetch, extract, and configure all the massive reverse-engineering binaries directly into ~/tools/—injecting them dynamically into your environment without forcing you to manually run brew, apt, or choco commands.
Just run the setup command, and it builds the entire penetration testing environment out of thin air:
# 1. Install via pip
pip install mobile-security-mcp
# 2. Run the Zero-Touch Setup (installs apktool, jadx, adb, frida, etc.)
python -m mobile_security_mcp --setup
🛠️ The Arsenal (Tools for Agents)
When an AI Agent connects to this server, they gain autonomous execution capability over the following tools:
Static Analysis & Reversing
apk_decompile: Unpacks APK viaapktool(Smali).apk_decompile_java: Hardware-accelerated source code extraction viajadx.apk_identify: Usesapkidto fingerprint packers, obfuscators, and SDKs.apk_scan_secrets: Scans the codebase for high-entropy secrets and keys.search_strings: Ultra-fast regex string hunting over decompiled code.
Dynamic Instrumentation (Frida)
frida_spawn: Spawns an app with early-instrumentation capabilities.frida_attach: Attaches to a running application process.frida_inject: Pushes raw JS or executes library bypass scripts live in memory.objection_run: High-level commands to explore application memory, classes, and SSL.
RASP & Anti-Tamper Bypass
rasp_identify: Identifies active enterprise app protections (Zimperium, DexGuard, Promon, Arxan).rasp_bypass: Dynamically generates targeted Frida bypass scripts for root detection, SSL pinning, and emulator checks.
Cross-Platform Scaffolding
hermes_decode: Extracts and decompiles React Native.hbcbundles to raw JSX.flutter_blutter: Scaffolds Flutter engine un-stripping and dart-compile recovery.
Device Control & Visuals
adb_shell/adb_pull/adb_push: Direct device bridging.scrcpy_start: Starts a background hardware-accelerated screen mirror.scrcpy_screenshot: Takes a pristine UI screenshot so the Agent can visually understand the app state.
Manipulation & Signing
apk_sign: Zipsigner & uber-apk-signer automation.apk_rebuild_sign: Re-compiles a modified Smali directory and re-signs it for immediate device installation.
🧠 Master Agent Workflow
This server ships with a massive built-in knowledge-base (master-agent-workflow) that AI agents read when they boots up. It enforces strict, logical reverse engineering methodologies, forcing agents to:
- Start with static mapping instead of blind dynamic analysis.
- Establish "Memory Profiles" using
memory_writeto keep persistent states over long sessions. - Consult built-in escalation playbooks (
bypass-ssl,bypass-root) if they get stuck.
🚀 Installation & Agent Integration
Claude Code
// .claude/mcp.json
{
"mcpServers": {
"mobile-security": {
"command": "python",
"args": ["-m", "mobile_security_mcp"]
}
}
}
Cline (VSCode)
"cline.mcpServers": {
"mobile-security": {
"command": "python",
"args": ["-m", "mobile_security_mcp"]
}
}
🤝 Contributing & Requesting Tools
We want to build the ultimate open-source, AI-driven Mobile Security framework. We welcome forks, pull requests, and community-driven knowledge!
Visit the Repository: github.com/mobile-security-mcp/mobile-security-mcp (Replace with actual repository link)
Have a tool suggestion?
If you maintain a fork or just love a specific open-source tool (like MobSF, RMS, Medusa, etc.), please open an issue at the link above! We are actively looking to add new handlers for:
- iOS decryption and LLDB bridging.
- Advanced unpacking tools.
- Web3 / Wallet security analyzers.
Feel free to fork the repo, create a new handler in mobile_security_mcp/handlers/, and submit a Pull Request!
Disclaimer: This tool is for educational and authorized penetration testing purposes only. You are solely responsible for ensuring you have explicit written permission before testing any application.
Metadata
Release files for mobile-security-mcp 0.1.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mobile_security_mcp-0.1.4.tar.gz | 64.9 kB | Without provenance | Details for mobile_security_mcp-0.1.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mobile_security_mcp-0.1.4-py3-none-any.whl | Python 3 | none | any | Details for mobile_security_mcp-0.1.4-py3-none-any.whl |
Total release size: 142.1 kB
Release files / mobile_security_mcp-0.1.4.tar.gz
| Download URL | mobile_security_mcp-0.1.4.tar.gz |
|---|---|
| Size | 64.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bb86e104ad830cf320d6eafd3841b34db4c2ee36410633139a5a0d1ca2ba9d63
|
|
BLAKE2b-256 checksum How to use checksums |
a6e6fb9f084dd1a70cd42943c4ff5db87c24404348f35a120136a10f8619dc17
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.0
|
Release files / mobile_security_mcp-0.1.4-py3-none-any.whl
| Download URL | mobile_security_mcp-0.1.4-py3-none-any.whl |
|---|---|
| Size | 77.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f9bfe6ed890e9195619b695553f6e63d17f3044dfb623f12529a2fcfdba876cf
|
|
BLAKE2b-256 checksum How to use checksums |
5794679534f72079dc50859a752a31fb841c153b092f7cdb56b11a752c3e659b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.0
|
Security for mobile-security-mcp 0.1.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.