MCP App StoreMCP App Store
from guardian-cli1,447
An AI-driven, production-ready CLI that automates authorized penetration testing workflows, orchestrating planner, tool, analyst and reporter agents to produce
Guardian CLI provides an end-to-end, AI-orchestrated penetration testing pipeline. It coordinates multiple specialist agents (Planner, ToolAgent, Analyst, Reporter) and a library of security tool wrappers to run reconnaissance, scanning, analysis and report generation. Outputs include richly evidence-backed Markdown, HTML or JSON reports and session artifacts that link findings to raw tool output and AI reasoning traces.
Use Guardian when you need an automated, repeatable pentesting workflow for authorized security assessments: web app discovery, network scans, vulnerability sweeps, or full autonomous AI-driven pentests. It's suitable for security teams who want reproducible YAML-defined workflows or ad-hoc scans with auditable evidence capture.
init, scan, recon, analyze, report, and workflow run. (Note: has_scripts=false in fetch metadata indicates no separate scripts/ dir tracked by the discovery script.)Inferred compatible tools: command-line AI providers and integrations (OpenAI, Anthropic/Claude, Google Gemini) and CLI-focused agents (Copilot-style CLI assistants, Code/Terminal agents).
Guardian CLI is a multi-agent AI penetration testing orchestration tool with 4 specialized agents (Planner, Tool, Analyst, Reporter) and 19 integrated security tools. The SKILL.md is thorough and well-structured with clear CLI commands, YAML workflow definitions, and configuration schema. No bundled scripts to test. The tool wraps common pentest tools (nmap, nuclei, sqlmap, etc.) via asyncio subprocesses, which is a shell injection risk surface, though the config includes safe_mode and scope blacklists. Intended for authorized testing only with legal disclaimers.
Security tool with legitimate authorized-testing purpose and legal disclaimers. Not malicious, but the shell subprocess wrapping pattern (-12 for shell injection risk) and config allowing API keys in YAML files (-12 for hardcoded credential risk potential) bring security score to 62. Architecture is strong: clear agent pipeline, YAML workflow system, modular tool wrappers. Code quality is good based on SKILL.md documentation but can't verify script behavior since none are bundled. Usefulness is moderate — pentest automation is valuable but niche audience, and requires significant external tool setup.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
TradeOS
Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.