Search

Security scanner for MCP servers. Think `npm audit` for the Model Context Protocol.

MCP proxy server with behavioral profiling, security scanning, risk gating, and safe execution

AI-powered multi-agent security platform. 12 agents scan 50+ attack classes. Red team your code before attackers do.

Security scanner for Model Context Protocol servers — catch tool poisoning, prompt injection, and supply-chain attacks before your AI agent runs them.

Open-source security scanner for MCP servers. Audits 17 AI tool clients for secrets, prompt injection, supply-chain risks, and 17 check classes. npx mcp-scan@latest

Security scanner for the AI agent ecosystem: MCP servers, Agent Skills, AGENTS.md / rule files, and agent tool code. Detects prompt injection, tool poisoning, data exfiltration and supply-chain risks. Zero dependencies.

MCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. One command grades it A–F, catching credential theft, tool-description poisoning (prompt injection), and install-script payloads by running i

AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.

ESLint plugin for Anthropic SDK security — catches hardcoded API keys in the Claude client options.

Security scanner for MCP-connected AI agent pipelines

A comprehensive MCP configuration scanner with client-aware security analysis.

MCP security proxy — protect any MCP server with customizable policies, path/command constraints, rate limiting, and audit logging. Zero code changes required.

Input firewall for AI agents: scan text and files before an agent reads them. Local, no network.

Authorization proxy for another MCP server: a rule check and AI judges approve each tool call

AI security testing — find security vulnerabilities in LLM apps, chatbots, AI agents, MCP servers, and RAG systems. Mapped to OWASP (LLM, Agentic, MCP) and NIST AI RMF.

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.

High-performance zero-dependency static analysis tool enforcing NASA Power of Ten reliability and security rules across 20 programming languages (JS/TS, Python, C/C++, Go, Rust, Java, Ada, C#, Fortran, Haskell, Kotlin, Lua, PHP, Ruby, Scala, Swift, Zig, J

AI-powered code security auditor. Scans GitHub repos for vulnerabilities with OWASP/CWE references and remediation guidance.

Standalone security daemon for IDE-agnostic AI agent security

🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.