"Understanding Inference Models" matching MCP servers:

An MCP server that runs curated adversarial prompts against local Ollama models to test guardrails, scoring responses with heuristic verdicts for human review.

Enables AI models to search and retrieve offline security knowledge from over 20 curated sources including HackTricks, PayloadsAllTheThings, and OWASP guides, via the Model Context Protocol.

Enables large language models to read and write IDA Pro databases through structured tool calls for reverse engineering, binary analysis, and hook development. Provides broker-based routing, SQLite-backed static caching, multi-instance analysis, and both cached and live IDA API queries.

MCP server for security-testing AI models, exposing garak vulnerability scanning and URL/MCP-endpoint scanning as callable tools. It lets agents probe LLM endpoints for jailbreaks, prompt injection, and data leakage, and classify URLs or screen remote MCP endpoints for prompt-injection payloads.

Bridges large language models with the Cobalt Strike C2 framework, enabling AI assistants to control adversary simulation workflows through natural language.

Provides a bridge between large language models and the Metasploit Framework, enabling AI assistants to access and control penetration testing functionality through natural language.

An MCP server that audits installed MCP servers, revealing their credentials, tool capabilities, and security risks. It enables users to assess and monitor the access granted to AI models.

Connects AI assistants to a Kali Linux terminal for executing security tools, managing interactive shell sessions, and performing penetration testing, CTF challenges, and security research tasks.

Bridges large language models with the Metasploit Framework to enable natural language control over penetration testing workflows. It provides tools for searching modules, executing exploits, generating payloads, and managing active sessions.

Enables AI models to interact directly with network services via raw TCP sockets, supporting multiple concurrent connections, buffering, and automated responses.

Enables Claude Code to leverage OpenAI models for expert code review, deep architecture analysis, and security audits, with automatic markdown report generation.

Frida MCP server enables AI models to perform dynamic analysis on mobile and desktop platforms via standardized interfaces, with cross-platform device management, script injection, and built-in hook scripts.

An MCP server that connects AI clients to a Linux terminal for real-time automated penetration testing and CTF challenge solving. It enables AI models to execute terminal commands and interact with offensive security tools like Nmap, SQLMap, and Gobuster.

An MCP server that enables AI models to perform Android dynamic analysis using Frida, including spawning and attaching to applications, listing apps, and injecting scripts.

A production-style MCP server providing AI models with cybersecurity tools including port scanning, WHOIS, DNS, threat intelligence, CVE lookup, and more.

A demonstration server that allows large language models to perform penetration testing tasks autonomously by interfacing with the Mythic C2 framework.