Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
mcp-server-security-audit
MCP serversScan websites for security vulnerabilities, headers, TLS, and email security.
mcp-server-security-audit@1.0.3 -
notebooklm-mcp-secure
MCP serversSecurity-hardened NotebookLM MCP with post-quantum encryption
@pan-sec/notebooklm-mcp@2026.5.0 -
SecurityTrails
Public APIsDomain and IP related information such as current and historical WHOIS and DNS records
-
Security Feeds
MCP serversSecurity Feeds MCP.
@pipeworx/mcp-security-feeds@0.2.1 -
Security Mcp
MCP serversMCP server for Security
-
awesome-claude-video-skills
SkillsOpen-source skills and toolkits that let Claude Code, Codex and other coding agents make video. 180 repos by type, each security-graded. English / 中文.
git clone https://github.com/zhuyansen/awesome-claude-video-skills.git -
magpie
SkillsAgent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.
git clone https://github.com/apache/magpie.git -
destructive_command_guard
Agents & frameworksA fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents run them. 50+ security packs (databases, Kubernetes, Docker, cloud, Terraform), heredoc/inline-script scanning, CI scan mode, and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor, and more.
git clone https://github.com/Dicklesworthstone/destructive_command_guard.git -
agentic-ai
AI repositoriesAgentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.
git clone https://github.com/mahmoudrabie/agentic-ai.git -
airlock
Tools & appsRun multiple AI agents and untrusted code in isolation. One command spins up a disposable Podman container — your SSH keys, dotfiles, and env files stay safe.
git clone https://github.com/besoeasy/airlock.git -
awesome-llm-observability
Skills50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
git clone https://github.com/ContextJet-ai/awesome-llm-observability.git -
agent-skills
SkillsThe definitive collection of cross-platform Agent Skills. Compatible with Claude Code, Codex, Cursor, OpenClaw, Gemini CLI, Copilot, Hermes. Curated weekly. Higher quality than any alternative.
git clone https://github.com/JPeetz/agent-skills.git -
AWS IoT Secure Tunneling
Public APIsIoT Secure Tunneling IoT Secure Tunneling creates remote connections to devices deployed in the field. For more information about how IoT Secure Tunneling works, see IoT Secure Tunneling .
-
Bright Security
MCP serversEnables AI agents to access Bright Security tools for app discovery and security testing.
-
Website Security Audit
MCP serversPassive security audit of a public website: HTTPS, headers, cookies, TLS, DNS, email, security.txt
@eazetech/website-security-audit-mcp@0.1.1 -
securessmtp
MCP serversSend email, manage sending domains, and read delivery analytics from your SecureSMTP account.
-
SecureNow
MCP serversProduction security for Node.js apps: investigate live attacks, block IPs, tune detections.
securenow@8.12.4 -
dvalincode
MCP serversDeterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.
dvalincode@0.23.0 -
agent-security
MCP serversSecurity scanning and threat detection for AI agents
agent-security-mcp@0.1.3 -
securityscan
MCP serversSecurity for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.
securityscan-mcp@0.2.0 -
securityscorecard-mcp
MCP serversCommunity-built, comprehensive MCP server for the SecurityScorecard API (unofficial).
@callmarcus/securityscorecard-mcp@2.0.0 -
contract-security-scanner
MCP serversMCP smart contract scanner with NEAR-focused security context.
mcp-contract-security@0.1.1 -
cc-safety-net
Agents & frameworksA pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
git clone https://github.com/kenryu42/cc-safety-net.git -
security-controls
MCP servers1,451 security controls across 261 frameworks with bidirectional mapping
security-controls-mcp@0.4.0
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.