"Using llama.cpp and Searxng with local models" matching MCP servers:

Exposes AI-augmented network reconnaissance and evasion capabilities as callable FastMCP tools, enabling natural language orchestration of host discovery, service fingerprinting, CVE mapping, and attack chain synthesis.

Exposes a hardened Docker container with Kali Linux security tools (nmap, sqlmap, dig, whois, etc.) as MCP tools, enabling network reconnaissance, web analysis, and vulnerability scanning through natural language commands.

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

Local-first, zero-egress security scanner for AI-generated / "vibe-coded" JS/TS. Bundles Opengrep, Gitleaks & Trivy behind one CWE-keyed schema and adds AI-code-specific checks (client-side secret exposure, Supabase RLS, prompt-injection & LLM-output XSS sinks). No account, no telemetry.

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 AI assistants to run Offensive360 SAST scans on local codebases, returning security findings with file/line, severity, and fixes, plus scan status tracking.

A local MCP server that scans repository dependencies for known vulnerabilities (CVEs) using OSV.dev, enriches findings with NVD and CISA KEV data, and supports triage, remediation, and accepted risk management directly from an AI coding assistant.

Enables comprehensive vulnerability scanning using Nuclei scanner with support for single targets, network ranges, and cluster-wide security assessments with customizable severity levels and automated scheduling.

Enables AI assistants to perform Active Directory reconnaissance by enumerating users, groups, computers, trusts, and password policies using ldapdomaindump on a remote Kali host via SSH.

Enables AI assistants to perform domain reconnaissance using theHarvester OSINT tool, including email harvesting, subdomain discovery, DNS brute force, and Shodan integration, via SSH on a Kali Linux host.

AI-powered penetration testing reasoning engine (MCP server) for attack path planning, step scoring, and tool recommendations using Beam Search and Monte Carlo Tree Search.

Enables AI assistants to perform web content discovery scans using feroxbuster on a remote system via SSH, with support for recursive scanning, filtering, and background execution.

Enables structured HTTP request creation and local file ingestion for LLM integration with Burp Suite, reducing malformed requests and token costs.

A Model Context Protocol (MCP) server that provides comprehensive network scanning capabilities using nmap.

Enables red-team and blue-team security workflows on BlackArch Linux by wrapping local tools like nmap, gobuster, nikto, and hydra as MCP tools, with scope-gating that prevents unauthorized scanning against any target not explicitly listed in a local scope.yaml file.

Enables local-first static and optional controlled dynamic analysis of Android APK artifacts, with provenance-aware downloads, Markdown reports, and structured security findings via MCP stdio tools.

An AI-powered penetration testing reasoning engine that provides automated attack path planning, step-by-step guidance for CTFs/HTB challenges, and tool recommendations using Beam Search and MCTS algorithms.

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.

Manual listener MCP server that bridges OpenCode with local security tools via a Flask HTTP service, enabling AI-assisted security operations.

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