Search

Open-source website, API and mobile app security toolkit. Find weaknesses with SAST, IDOR review, secrets, SBOM/SCA and IaC checks; prioritize fixes with local MCP.

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1700+ vulnerability rules with AST & taint analysis, LLM-powered semantic code review, auto-fix. For Claude Code, Cursor, Windsu

The ultimate OWASP MCP Top 10 security checklist and pentesting framework for Model Context Protocol (MCP), AI agents, and LLM-powered systems.

Security scanner and runtime policy gateway for MCP servers

The calm guardian for AI, agent, and MCP code — a zero-dependency, standards-anchored AI security toolkit for developers and security reviewers.

MCP server that audits other MCP servers' tool definitions for insecure patterns — excessive-agency tool names, shell/eval/SQL/SSRF sinks fed by raw tool input, overly permissive schemas, hardcoded secrets, and wildcard CORS

Model Context Protocol server for the React Native Security Toolkit: exposes deterministic security findings, with severity and OWASP/CWE references, to whichever AI model you already use. No API key, no vendor, no source upload.

Static analysis and attack-surface scanner for AI agents — SAST for prompts, tools, MCP servers, and agent workflows. Detects capabilities, prompt risks, tool permissions, and governance gaps before deployment.

Vouch — the trust layer for AI agents. Vet Skills and agents, profile them with CVs, and vouch only for the safe ones (hybrid static + LLM analysis).

Test your MCP servers for breaking changes. Checks capabilities, invokes tools, detects schema drift between versions.

Runtime enforcement proxy for MCP agents: capability manifests, session taint, trifecta invariant, hash-chained audit

The Sudo Command for AI Agents. Execution Security for Claude Code & MCP.

The Sudo Command for AI Agents. Execution Security for Claude Code & MCP.

The first open-source AI agent built for offensive security. Autonomous pentesting from your terminal.

MCP Server Security Scanning Tool - an LLM-driven autonomous agent for code audit and vulnerability detection

Correctover Security Scanner — CCS audit for MCP configurations. Detects RCE, SSRF, credential hijacking against OWASP AISVS 1.0.

Open-source MCP/A2A security gateway — policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit for every AI agent tool call. OWASP ASI 2026 compliant.

AI Agent Security Middleware — 8-layer defense against prompt injection, data exfiltration & dangerous commands. DLP model: use data freely, block external leaks. Zero dependencies. SDK + OpenClaw plugin. Supports LangChain, AutoGPT, Claude Code, Cursor,

Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more

AI agent runtime security scanner - detect malicious behavior in Claude Skills, MCP Servers, Codex Plugins, and more