Search

A default-deny authorization firewall for AI agents and MCP servers, enforcing capability-based security policies across tools, files, network, and system commands.

MCP server that wraps aircrack-ng, enabling AI assistants to run and automate WiFi security assessments (scanning, handshake capture, cracking) for authorized penetration testing.

Enables AI agents to perform endpoint security scanning using AlienVault OTX and VirusTotal, including multi-platform scans, threat intelligence queries, and scan data persistence.

Security gateway for AI agents using MCP: pins tool manifests, enforces policy before execution, binds human approval to the exact payload, and records tamper-evident evidence. FastAPI, MCP 2025-11-25.

Argues against a security finding or a draft bug bounty report before you submit it.

Evidence-based preflight security scanner for Model Context Protocol (MCP) servers.

MCPS -- MCP Secure. Cryptographic identity, message signing, and trust verification for the Model Context Protocol.

MCP security trust-check alias for AgentSecurityLens: safe install decisions before agents install MCP servers.

AI Agent Security — scan every tool call for secrets, PII, destructive commands, and prompt injection. Runs locally, zero dependencies, no signup required.

Client-side instrumentation for API and AI agent security monitoring. Django middleware, MCP server instrumentation, an Envoy AI Gateway OTLP bridge, and a MuleSoft Flex Gateway policy that capture request, tool-call and LLM traffic and stream it to Cerberus.

MCP security scanner — Toolfence scans any Model Context Protocol server and reports the risks your AI agents inherit: tool poisoning, prompt injection, tool drift, over-broad scope, context-cost runaway. 12 checks, one command, CI-ready exit codes. Open source, Apache 2.0. npx toolfence <url> — this repo is the landing site.

OWASP harness for executable security regression testing of agentic applications and MCP-integrated systems.

Nimbus - AWS Security Assessment MCP Server - 45 Tools with Full OWASP MCP Security

Vehicle security toolkit — CAN bus, UDS, J1939, ICSim bridge & Textual TUI for automotive security research.

AWS Network MCP Server – VPC inspection, security group analysis, ENI details, flow log queries, and IP address lookup for security investigations

Free passive security scanning for AI agents. Check any domain for email spoofing (DMARC/SPF/DKIM), TLS, security headers, exposed files, and subdomain takeover risk — using public information only, no intrusive probing.

Offensive-security toolkit: port scanning, L7/WAF detection, mTLS, certificate analysis, OWASP Top 10, AI/LLM OWASP Top 10 black-box probing, and MCP endpoint security scanning

MCP server that audits shipped apps for how easily they can be reverse engineered — exposed source maps, missing minification/R8/.NET obfuscation, debug info and unstripped symbols, debuggable flags, Electron fuses, unsigned binaries and embedded secrets

Counterspell for hallucinating agents. Python SDK that breaks the illusion on every tool call, API response, and MCP handoff before bad outputs propagate.

Temporary package placeholder for staged publishing