Best Sec AI Skills & MCP Servers

VibeSecurity — Auditoria de segurança para quem cria com IA. Secrets, vulnerabilidades e rotas sem auth.

MCP server that gives AI agents (Claude, Cursor, Copilot) deep understanding of your codebase patterns, conventions, and architecture. Query patterns, security boundaries, call graphs in real-time.

MCP server that lets AI assistants read Overleaf projects, parse LaTeX document structure, and push section-level edits back via Git.

PerfAI MCP Server - Security, Design & Quality Analysis with Auth0 Authentication

OpenCode plugin + MCP server + skill that runs an automated GitHub Copilot PR review loop: request review, wait deterministically via `gh run watch`, triage every comment, push fixes, reply, resolve, gated merge. Solves the silent-fail of github_request_c

Security scanner for AI agent tools. Local static scan of MCP IDE configs (41 rules, toxic flow heuristics, AAuth visibility, auto-fix, tool pinning). Optional proxy + in-browser dashboard: traffic, findings, AAuth Explorer, YARA, Playground. Smart Scan o

MCP server for DM8 database operations with enhanced security. Provides read-only database access via Model Context Protocol.

Security co-pilot for AI agents. Scan for vulnerabilities, verify governance, audit MCP servers, and generate compliance reports — all from Claude, Cursor, or any MCP client.

GARL Protocol MCP Server — cryptographic verification for AI agent actions. 28 named tools: submit signed Action Receipts (v0.1), query multi-dimensional Trust Vector, issue/verify/revoke capability tokens (JWT-shaped + ECDSA-secp256k1), Capability Gate p

MCP security trust layer. Scan packages, inspect repo MCP dependencies, generate Policy Gate setup, check exposure, and query abuse data.

MCP server for markdown files — search, extract sections, list headings, find code blocks across your docs directory

Official MCP server for IP geolocation, IP security, abuse contacts, ASN, timezone, astronomy, and user-agent parsing.

Deploy and manage apps on EigenCompute TEE — trusted execution environments with hardware-level isolation, encrypted secrets, and attestation. Works as MCP server for Cursor/Claude Desktop or as Claude Code skill.

CuratedMCP's local-first action firewall for MCP servers

Scaffold a Voidly Pay-enabled AI agent in one command. Pick a template (paid MCP server, Hono x402 endpoint, FastAPI x402 endpoint, or zero-code universal proxy) and you're running in under 60 seconds.

MCP server for Loopuman — The Human Layer for AI. Give AI agents instant access to verified human workers in 30+ countries. Post tasks, competitions, and social contests. Workers paid in seconds via blockchain.

MCP server for searching past Claude Code conversation history. Local BM25 search over JSONL logs with persistent index, secret redaction, solved-hint, and instant claude --resume.

AI agent OS for vibe coders — MCP server for Claude, Cursor, Windsurf & Lovable. Security audits, SEO, performance, design tokens, copywriting and 76+ dev tools in one CLI.

MCP server for Firewalla MSP API - provides CRUD operations for all Firewalla MSP endpoints

MCP server for Wiz cloud security platform — query vulnerability findings by repo and severity

Scaffold a personal LLM wiki (Karpathy pattern). MCP-ready, multi-agent, publishable. Zero-prompt install for IM agents (OpenClaw, Hermes, Codex, Claude Code).

MCP server for Envault CLI operations

MCP server for cryptographic AI agent governance. Seal policy artifacts, enforce at runtime, prove with signed receipts and offline-verifiable evidence bundles.

The runtime security layer for AI agent commerce. Drop-in CLI + MCP server — blocks hallucinated purchases and keeps card credentials out of agent context. It only takes 0.1% of hallucination to drain 100% of your wallet.