Search

Security proxy that automatically wraps MCP servers with real-time monitoring and policy enforcement

CLI for AI agent security evals, CI regression gates, and local runtime control

MCP red teaming & security scanner — enumerate, probe, and exploit Model Context Protocol servers

Zero-Go Model Context Protocol (MCP) Server for Cybermes Autonomous Security & Diagnostic Framework

Security scanner for MCP servers — detect prompt injection, credential leaks, exposed endpoints, and tool poisoning

Adversarial MCP server benchmark suite for testing tool-calling security, drift detection, and proxy defenses

MCP server security testing with live adversarial checks, a reproducible demo, HTML reports, and a GitHub Action.

Security scanner for AI agents and MCP servers. Scan local codebases or remote MCP servers in seconds.

Provenance-aware security proxy for AI agents: block prompt-injection actions at the MCP tool boundary.

Runtime security proxy for the Model Context Protocol (MCP). The Cloudflare WAF for AI agents. Powered by ClawGuard.

CLI and GitHub Action for static security scanning of JavaScript/TypeScript Model Context Protocol (MCP) server repositories.

Active, confirmation-driven security scanner for MCP (Model Context Protocol) servers - Burp Active Scan, for MCP.

Black-box security scanner for MCP servers — fires curated single-call probes and classifies findings. No LLM in the loop.

10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.

Claude-first Slack MCP for self-host or managed Cloud, with Gemini CLI, deployment review, and secure-default HTTP.

Security gateway for MCP servers — enforce tool access policies, audit AI agent activity, and detect exposed secrets.

Security gateway for Model Context Protocol (MCP) traffic. Blocks prompt injection, cross-repo exfiltration, and destructive commands.

Agentic security control plane for MCP and AI agent tool calls. MCP-native policy gateway with topology discovery and audit.

🔒 Simulate adversarial behaviors to test and strengthen MCP defenses without real exploitation or risk, ensuring robust security evaluations.

The CVEasy open lab — runnable security harnesses, red-team probes, and experiments. Good-faith open source from CVEasy AI.