Mobdev
Mac app that lets AI agents drive iPhones, iOS simulators and Android: tap, type, install, logs.
やりたいことや使っているアプリで検索し、カテゴリで絞り込めます。
リポジトリのGitHubスターが多い順。スターは関心の高さで、品質ではありません。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Mac app that lets AI agents drive iPhones, iOS simulators and Android: tap, type, install, logs.
Checks declared npm/PyPI dependencies against real registries to catch slopsquatting
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit
DNS record enumeration, misconfiguration and dangling-subdomain detection
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Ask what your team decided in meetings, get your standup, and update Jira/Linear-synced tasks.
MCP server for Dynatrace Managed to access logs, events, and metrics.
Structural code-quality tools for AI coding agents.
Deep linking for iOS, Android, Flutter & React Native. Firebase Dynamic Links alternative.
MCP server with WebdriverIO for browser and mobile app automation (iOS/Android via Appium)
Persistent engineering memory designed to follow developers across coding agents.
Read and submit one AI Form API form for a person, with a one-time fill code. No login.
Focused repository context for Claude Code and Codex, with per-session token usage receipts.
Explore MITRE CWE weaknesses, CAPEC attack patterns, mitigations, code examples, and mappings.
Audit-first test strategy MCP server for repository-native test planning.
Mac networking for agents: per-app traffic, Wi-Fi, latency, DNS, why a host fails and keep-awake.
Passive external attack-surface mapping: CT subdomains, DNS, TLS, HTTP posture, RDAP/WHOIS, Shodan.
Local code graph and solution memory for coding agents via CLI and MCP.
Read-only Kubernetes MCP server: inspect resources, logs, events, and metrics. Secrets are masked.
GitHub security scanning, code audit, and workflow automation for repositories.
MCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).
Real-browser UI checks and speed audits for coding agents, catching fixes that only hide the bug.
9 local Python protection tools, delivery checks and traceback reverse mapping. No telemetry.