Search

Plain-English website security check for agents: certificate, headers, scripts, forms, spam.

Static security linter & auditor for Model Context Protocol (MCP) servers and AI agents 🛡️

The Reference Architecture for Local AI Governance & Firewalling. Secure, deterministic protection for Agents, MCP, and LLMs.

AI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints

A security control plane for LLM and agent applications: detection, provenance, risk, authorization, policy and enforcement.

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

RedVector AI - AI-powered penetration testing and cybersecurity automation framework for security researchers and ethical hackers.

Signed provenance labels and taint-tracking policy for LLM agent security. The core library behind AgentMesh.

Open-source DNS & email security scanner. One MCP endpoint, 57 checks, zero install. Cloudflare Workers.

LLM security red teaming — Claude Code plugin + MCP server with 80+ attack plugins and 25+ mutation strategies

🔒 Security-scored directory for AI agent skills and MCP servers. 33,000+ scanned, 12% malware detection.

LLM security guardrails for Claude Code, for a self-hosted AgentGuards appliance — enforced entirely by hooks, no bundled MCP server.

Zero-trust AI security research engine built on MCP, Tauri v2, and Rust — with prompt injection defense and sandboxed tool execution

The MCP security scanner that actively exploits: prove SSRF, path traversal, command injection and more in MCP servers (OWASP MCP Top 10).

Local security scanner, hardening checks and optional stdio policy guard for Model Context Protocol (MCP) servers. Source beta by Nullvora.

7-phase security proxy for MCP agents. Defends against tool poisoning, description-code inconsistencies, path traversal, and authentication attacks. 115 tests.

Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.

MCP server for LLM-driven security testing via HTTPToolkit — capture analysis, mutation-based replay, audit trails for mobile and electron app pentesting

Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.

MCP server for secure AI agent authentication — lets Claude, Claude Code, and other LLM agents call APIs without exposing raw tokens or credentials to the model