Search

Compile MCP tool manifests into sandbox policies (bwrap, egress rules, and more).

Capability-based policy enforcement for agent CLI actions

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

Official TypeScript SDK and CLI for ArmorDesk: Enterprise AI Agent Control Plane, Governed MCP Gateway, and Cryptographic Trust Center.

Skill router and prompt-injection firewall for AI coding agents: give Claude Code, Codex and Cursor the right skills, MCP servers and tools for each task.

Kernel-to-MCP flight recorder for AI agents on macOS: attributes every exec, file access and socket to the agent and MCP tool call that caused it

Scan MCP servers & AI-agent skills for malicious patterns (prompt injection in tool descriptions, credential exfil, download-and-execute). 17 patterns / 60 signatures, zero-dep. Measured over 196 public MCP servers: 99% clean, false-positive rate calibrated 14.8% -> 1.0%.

The bidirectional firewall for MCP — scans inputs AND outputs, detects rug-pulls at runtime, zero config.

MCP server for the Guard ecosystem — config validation, docs search and live threat detection for fastapi-guard, guard-core and guard-agent.

SuricataMCP enables autonomous network traffic analysis using Suricata through a Model Context Protocol server, facilitating seamless integration with AI coding tools.

MCP Server for dependfix: expose scan/fix capabilities to AI assistants

🐍 🏠 - A Model Context Protocol (MCP) server for querying the CVE-Search API. This server provides comprehensive access to CVE-Search, browse vendor and product、get CVE per CVE-ID、get the last updated CVEs.

Micro-Cleanse Preprocessor: local secret-removal agent (with vault pack/unpack)

Local-first privacy MCP server for sensitive AI workflows

Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.

A local application firewall for coding agents. Little Snitch, but for AI agent tool calls.

MCP server for Burp Suite Professional's REST API.

Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.

Least-privilege policy wrapper for any GoHighLevel MCP server. Declare which tools an agent may call and with which arguments; everything else is refused and logged. Hides denied tools from tools/list. Redacted audit log.

Scanners flag CVEs. CheckExploit proves which ones actually reach your code — by running the real exploit against your actual code inside an isolated sandbox. Supports Python,Node repos; generates and verifies remediation patches. Built on OpenCode + MCP.