#ai-security

MCP Scanner

Advanced Shodan-based scanner for discovering, verifying, and enumerating Model Context Protocol (MCP) servers and AI infrastructure tools o...

MCP Client And Proxy

A universal MCP client with proxying feature to interact with MCP Servers which support STDIO transport.

Rampart

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do...

MCP Bastion

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detec...

Cerberus

🐺 Cerberus — local-first security gateway for AI coding agents. Intercept, risk-score & human-approve every tool call (Claude Code, Codex,...

Skillguard

Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads before you install.

Tengu

AI-powered penetration testing MCP server

Assay

Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the ker...

MCP Scanner

MCP server security scanner — CVE check, auth audit, tool poisoning detection

Tooltrust Scanner

Security scanner for AI agent tool definitions

Declaw CLI

Command-line interface for Declaw — security-first sandboxing for AI agents

Agentshield

MCP security scanner for Claude, Cursor, OpenAI Agents, LangGraph and CrewAI - offline Rust SAST with SARIF for GitHub Code Scanning