by vwww-droid
Mobile runtime detection workbench for AI (iOS and Android)
# Add to your Claude Code skills
git clone https://github.com/vwww-droid/MiraGuides for using mcp servers skills like Mira.
Last scanned: 8/27/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-08-27T15:02:44.717Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}Mira is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by vwww-droid. Mobile runtime detection workbench for AI (iOS and Android). It has 100 GitHub stars.
Yes. Mira passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/vwww-droid/Mira" and add it to your Claude Code skills directory (see the Installation section above).
Mira is primarily written in C. It is open-source under vwww-droid on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Mira against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Mobile runtime detection workbench for iOS and Android.
PYTHONPATH=. python3 -m mira.relay.server --host 0.0.0.0 --port 8765 --advertise-url http://<your-lan-ip>:8765http://127.0.0.1:8765 on your desktop.http://<your-lan-ip>:8765 in the app.docs/GETTING-STARTED.md.PYTHONPATH=. python3 -m mira.mcp.server --relay http://127.0.0.1:8765. MCP config: docs/MCP.md.Mira welcomes issues and pull requests from mobile security researchers, reverse engineers, Frida users, MCP users, and device testers.
CONTRIBUTING.md before opening a focused pull request.SECURITY.md first.Good starting points include native memory-safety review, Android and iOS device testing, Frida workflow examples, MCP client setup notes, and new reusable detection cases.

With Relay, you can temporarily expose an authorized session beyond the local network for cloud devices, expert review handoff, and fast evidence sharing.
docs/README.md: English documentation hub.docs/GETTING-STARTED.md: full setup, build, device connect, MCP, and CLI.docs/REMOTE-RELAY.md: public and LAN Relay startup flows.docs/MCP.md: Codex and Claude MCP integration.docs/IOS-APP.md: iOS app architecture and device notes.docs/NATIVE-ARCHITECTURE.md: shared PTY native architecture.docs/TOOLBOX.md: Android toolbox packaging and runtime release flow.docs/REPO-ARCHITECTURE.md: repository layering and entry-point layout.docs/THIRD-PARTY-NOTICES.md: third-party notices.GPL-3.0-only.