Library
86,671 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Domain Intelligence
Public APIsDNS, WHOIS/RDAP, SSL, subdomain enumeration, and email security in one parallel call
-
terminal-jarvis
PromptsIn the midst of all the tools out there that you can possibly use to keep track of them. Here's a "shovel" that just works to try them all out.
git clone https://github.com/BA-CalderonMorales/terminal-jarvis.git -
maruda
SkillsAI with a harness. Agent skills, rules, CI and security gates for AI-assisted development.
git clone https://github.com/northraystudio/maruda.git -
Reverse engineering skill for Claude Code and other AI coding agents.
git clone https://github.com/EncidXVII/claude-reverse-engineering-skill.git -
deliberation
Agents & frameworksAsk Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.
git clone https://github.com/antonbabenko/deliberation.git -
ZIP MCP server: create, inspect, verify, extract, canonicalize, merge, modify. 15 tools
zipnative-mcp@1.1.0 -
Aegis Security Skills
MCP serversRead-only library of 24 defensive cybersecurity skills: ATT&CK, ATLAS, DFIR, CTEM and more.
aegis-skills@1.5.0 -
YesTechie — UniFi Network & Security Integrator
MCP serversUniFi quotes, case studies and network, camera, access config guides from a nationwide integrator.
-
ATK Security Checks
MCP serversPQ TLS + cert checks; Wazuh rules tested on a real manager; PHP2Shell CVE check + fix steps
-
Power Strip Security
MCP serversPrompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402.
power-strip-security-mcp@0.2.0 -
72hours security check
MCP serversScan a public GitHub repo, explain risks, get fix prompts and rescan to confirm fixes.
-
SecureInput
MCP serversType API keys into a native inline input instead of the chat; delivered to a local command or .env.
secureinput@0.1.1 -
Secure Telegram
MCP serversTelegram MCP server: each AI client gets its own key, scoped to chosen chats. Read-only by default.
secure-telegram-mcp@0.3.3 -
Panda Web Security Tools
MCP serversSite/email/agent safety and monitors: SPF/DKIM, SEO, change + RSS monitors, hidden-AI, WHOIS (7).
panda-web-security-tools@0.2.0 -
covert-coder
Tools & appsCovert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.
git clone https://github.com/AnonymousNomad/covert-coder.git -
Mail Security Tools
MCP serversDMARC/SPF/DKIM/MX checks, email score, 100-domain bulk score, webhook watch alerts (x402 USDC).
-
Agent Skill & Config Security Audit
MCP serversScan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.
-
Dockerfile Security Audit
MCP serversAudit Dockerfiles for root users, baked-in secrets, curl-pipe-shell and unpinned base images.
-
aegis-security-mcp
MCP serversAI scam-shield for Web3: screen token contracts for honeypot/drain patterns. Aegis AI group admin.
-
Keeper Security MCP
MCP serversRead-only Keeper MSP posture across every client, with history, a change feed and no path to a
https://github.com/Servosity/msp-skills/releases/download/keeper-v0.1.3/keeper-mcp.mcpb@0.1.3 -
Keep Me Secure
MCP serversTells your coding agent whether your installed packages need patching, with advice on what to do.
ghcr.io/robertkeus/keep-me-secure-mcp:v1.7.0 -
agent-skill-security-escrow-auditor
MCP serversERC-8183 Agent Skill, Prompt & MCP Plugin Anti-Trojan Auditor & USDC Escrow on Base.
-
k11 API Security QA
MCP serversOWASP API Top 10 tests from your OpenAPI spec, plus scanner SARIF judged for release.
k11-api-security-qa-mcp@0.1.0 -
Draugr
MCP serversSecurity scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
https://github.com/draugr-dev/draugr/releases/download/v0.182.0/draugr-0.182.0.mcpb@0.182.0
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.