Search

Governed MCP workflows with policy validation, findings tracking, and review gates.

AI-powered vulnerability scanner for any codebase — fork of vercel-labs/deepsec with bun support, additional AI providers (openai-compat, ollama, opencode), and Windows compatibility fixes

Audit what an MCP server advertises to your agent — tool descriptions that read like instructions, and declared permissions that contradict described behaviour. Launcher for the Python CLI (requires Python 3.9+).

Live CORS misconfiguration probe: origin reflection, wildcard+credentials, null-origin, substring bypass. SAFE/RISKY/DANGEROUS. MCP + x402.

Local MCP safety gate for AI agents, paid per check with x402 on Algorand.

https://github.com/BeBraveBeKind/mcpskills-server

Dark web intelligence MCP server — HIBP, ThreatFox, ransomware tracking, Tor .onion access, blockchain intel, exploit search, stealer logs, malware analysis

Zero-trust MCP gateway — policy enforcement, secret redaction, and audit logging for AI-assisted projects

Safety-first MCP server for Discord with privacy-safe reads, audits, and reviewed administration

MCP server for depsight — query CVE, license, dependency and CI data from Claude / other agents

A macOS Control Plane that runs AI coding CLIs inside the Project boundary you choose.

Dynamic red-team harness for MCP agents: a transparent proxy that injects attacks, measures attack success rate, and ships an information-flow mitigation layer.

Official anysite agent skills + one-line setup: installs skills into Claude Code / Codex and registers the anysite remote MCP server. Includes the GTM bundle (CRM enrichment, signals, prospecting).

Mint, resolve, audit, and rotate scope-limited expiring access links (qURLs) for AI agents.

Pre-transaction trust firewall for AI agents: should-i-pay decisions, sybil forensics, liveness SLA (SweetAI x402 / ERC-8004)

ph — Scan Claude Code / Codex CLI / Gemini CLI plugins for malicious hooks, poisoned SKILL.md, and MCP tool-poisoning *before* you install. Uses your local LLM CLI as the judge — no API key required.

MCP server for Huntress — accounts, organizations, agents, incidents, and reports.

TypeScript SDK for the Gibson platform: connect-es bindings, Capability Grant auth, component registration, and an OpenAI-compatible LLM shim. Framework-agnostic.

CryptoData MCP Server - Real-time crypto market data, DeFi analytics, and on-chain intelligence...

Deterministic policy engine for AI agent tool calls: parse, sign, verify and evaluate AgentLaw policy manifests. No MCP dependency — embeddable anywhere.