Search

Dependency-provenance firewall for AI coding agents — blocks malicious packages, slopsquats, and prompt-injection aimed at the agent, at install time.

Runtime guardrails for AI agent MCP tools. Detect MCP configs, wrap risky servers with a policy proxy, and block dangerous tool calls at runtime.

MCP server for dossier automation standard - enables LLMs to discover, verify, and execute dossiers

Build-time permission checker for TypeScript and AI agents. Fails the pull request when code starts reaching a new server, file, secret, database table, risky MCP tool, or CI permission.

CI-first MCP supply-chain integrity gate: pin and verify the declared tool/resource/prompt surface of an MCP server, plus runtime tool-result inspection (guard/inspect).

Scan AI agent skills, plugins, MCP servers, and CLI tools (npm/PyPI/Go, cargo, release binaries, curl|bash installers) for malicious code before installation - one scan, every agent (Claude Code, Codex, Gemini, Hermes, OpenClaw). Powered by NVIDIA SkillSpector, Cisco mcp-scanner, Datadog GuardDog, VirusTotal + malcontent.

Static analysis scanner for MCP server code and multi-tenant SaaS applications. 57 deterministic rules covering tenant isolation, tool visibility, cache key scoping, RLS, IDOR, and credential vault isolation. MCP server for AI agent integration.

A security scanner for Claude Skills

Security, cost, and health audit for MCP infrastructure

MCP server that scans other MCP servers for prompt injection, data exfiltration, and privilege escalation. Add to your .mcp.json and let your AI agent audit its own tools.

Security scanner for MCP (Model Context Protocol) tools

Security scanner for AI agents and MCP server configurations

A deterministic security and reliability control plane for MCP tool execution.

Security scanning for websites, public repositories, and Open CLAW skills.

https://github.com/UPinar/contrastapi

MCPTROTTER — MCP Pentest Tool: 28 automated security checks for MCP servers

Safe, self-hosted ZAP operator for guided AI security scans and reports.

Metasploit-style exploitation framework for testing MCP servers and MCP security gateways.

Deliberately vulnerable MCP server (aka MCP Goat) for security training — 26 challenges across 4 difficulty levels (incl. a secure reference), a victim-agent harness, and one-command Docker deploy. Practice penetration testing against the Model Context Protocol.

SINT Bridge — MCP adapter: intercepts AI agent tool calls through the security gate