poki
Enables automated testing and interaction with iOS environments through a local MCP server.
Let AI agents operate a real iPhone. Local MCP server and agent, no jailbreak, no extra hardware.
- Ask Claude to perform specific tasks within mobile applications on an iPhone
- Automate repetitive manual testing workflows on a physical iOS device
- Find and report UI bugs by observing real iPhone screen interactions
Enables automated testing and interaction with iOS environments through a local MCP server. This closes the gap between LLM reasoning and physical mobile device execution without requiring complex hardware setups or security bypasses.
QA engineers and mobile developers automating functional testing on physical iPhone hardware via AI agents.
https://github.com/JosssphZhou/poki
By JosssphZhou
How to Get It
claude plugins install JosssphZhou/poki
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Perform specific tasks within mobile applications on an iPhone
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 639 GitHub stars; contributors unknown; last commit 0d ago; license AGPL-3.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
- License (AGPL-3.0) may restrict commercial use. Check with your legal team.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 639 GitHub stars; contributors unknown; last commit 0d ago; license AGPL-3.0.