An MCP Server that enables users to interact with Google's On-Demand Scanning API (v1beta1) through natural language, likely providing capabilities for vulnerability scanning and security analysis of containers and artifacts.
Enables Claude Code to leverage OpenAI models for expert code review, deep architecture analysis, and security audits, with automatic markdown report generation.
GDB Enhanced Features MCP server for remote debugging and CTF exploitation with 41 specialized tools including ROP search, format-string detection, and memory patching.
No-code LLM red teaming and prompt injection testing for chatbots and AI agents, for small businesses and Make, n8n, Voiceflow builders. 12 attack levels (fake manager, prompt injection, phishing, invented prices, AI Act Art. 50), A-F grade, ready-to-paste prompt fixes. Prompt mode needs no deployment; live mode tests webhooks and OpenAI-compatible bots. Endpoint: app.botarmor.eu/mcp
Enables LLMs to perform automated penetration testing and Active Directory reconnaissance through Mythic, with tools for executing PowerShell, AD recon, domain user enumeration, and Kerberoasting.
Enables users to run synthetic support-agent evaluations, preserve and inspect traces, score results deterministically, inject failures, and enforce release review gates through MCP tools, resources, and prompts.
Enables AI agents to perform passive security scans on domains, checking email spoofing (DMARC/SPF/DKIM), TLS weaknesses, security headers, exposed files, and subdomain-takeover risk without needing an API key.
An MCP server that lets an AI agent probe a live URL and confirm whether sensitive files (e.g., .git, .env, source maps) are genuinely served by fetching and validating the content, avoiding false positives.
An MCP server that runs curated adversarial prompts against local Ollama models to test guardrails, scoring responses with heuristic verdicts for human review.
A read-only MCP server for the Qualys PCI Merchant API that lets LLM assistants answer questions about PCI compliance posture, such as which hosts are failing PCI or listing high findings.
Connects an AI assistant to an already-running mitmweb session so it can read, search, diff, replay, and generate code from the same network flows shown in the UI.
This server enables AI-assisted APK reverse-engineering entirely on-device, orchestrating jadx, apktool, adb, frida, and APKiD through a job/workflow engine, and exposing those agents as native MCP tools for Claude without any cloud dependency.
Enables bug bounty hunters to browse programs, inspect scope details, track scope changes over time, and receive personalized, recency-boosted program recommendations based on their skill profile.
Enables interaction with NowSecure Platform for listing applications, retrieving remediation findings, and generating remediation PDFs via REST and GraphQL APIs.
Static security scanner for AI-generated (vibe-coded) Supabase and Next.js apps. Runs as an MCP server so an LLM can scan, explain findings, and produce fixes while it writes code, all locally and offline.
Enables AI agents to drive live Hack The Box labs through the real HTB Labs API — spawning, resetting and extending machines, submitting user and root flags with difficulty ratings, browsing challenges, and switching or downloading VPN configurations for the authenticated account. Every call hits the live API rather than cached content, with destructive actions annotated so hosts can gate them behind consent.
Gives AI agents threat-intelligence verdicts for IPs, domains, URLs and hashes, CVE lookups with EPSS and CISA KEV data, and a prompt-injection gate that scans untrusted text before the agent acts on it. Agents can also batch-check up to 100 indicators, hunt brand-lookalike domains, and track scan and request quotas.
Enables AI assistants and CLI users to run automated bytecode security audits of EVM smart contracts on Base Mainnet, detecting risky opcodes and interface signatures, scoring risk, and unlocking verified results via x402 USDC micropayments.
A scope-aware bug-bounty & reconnaissance MCP server that works out of the box on the Python standard library and augments itself with your favourite CLI tools when they're present.
Enables an agent to probe a remote MCP endpoint with a few read-only, anonymous requests and get back a timestaped, evidence-grade verdict on whether its tool inventory is exposed without authentication, who can re-verify it themselves. Verdicts include unauthenticated-surface, authenticated-ok, and error classes, with no handshake forgery or exploit payloads.
Enables AI assistants to run Offensive360 SAST scans on local codebases, returning security findings with file/line, severity, and fixes, plus scan status tracking.
Audits AI agent skills for safety using static, semantic, adversarial, and supply-chain analysis, providing scores and risk flags. Can be run via CLI, CI, or as an MCP tool from Claude Code, Cursor, and Codex.
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 AI agents to inspect websites read-only for manipulation aimed at search engines and AI assistants — sneaky and open redirects, hidden text and links, injected spam, hijacked metadata, and hidden prompt-injection or prefill-based recommendation poisoning — with every finding backed by deterministic rule evidence, severity, and remediation. Scans are stored locally, redirect chains can be traced hop-by-hop, and results can be exported as markdown or JSON reports.
Enables Claude to scan a website's HTTP security headers and receive an A–F grade against OWASP best practices, including per-header pass/warn/fail results and copy-paste fixes for missing headers.
Security scanning for MCP servers from the inside out. Provides runtime inspection, AST-based static analysis, config audit, dependency analysis, and OWASP MCP Top 10 compliance in a single MCP server.
An MCP server that enables AI assistants to analyze Android APK and iOS IPA files for security issues through natural language conversation, including permission auditing, secret detection, and SDK enumeration.
Security checks for code an AI agent is about to trust. vetcode_guard checks a command before it installs packages or adds an MCP server: made-up names, look-alikes, malware advisories, brand-new releases, and the archive read without running it. vetcode_scan reads a folder for malware, supply-chain attacks, attacks on agents, leaked secrets and risky config. Local, zero dependencies.
A Model Context Protocol (MCP) server for Gobuster that enables AI assistants to perform directory/file, DNS, virtual host, S3 bucket, and TFTP enumeration on a remote Kali Linux host via SSH.
Enables dynamic management and execution of proxy chains on a remote Linux host via SSH, allowing AI assistants to route network traffic through proxies for privacy and security testing.
A universal digital fingerprinting MCP server that combines 103 techniques across TCP, TLS, SSH, HTTP, DNS, and more into a single interface for AI agents, enabling full-spectrum fingerprinting on demand.
Enables interactive Ghidra reverse-engineering inside an AI client by rendering live decompiler, function browser, and call graph views. Users can click symbols to rename them and follow calls to navigate, all without leaving the conversation.
Enables AI assistants to run Kali Linux security tools in an isolated Docker container for tasks like network scanning, port checking, and service enumeration.
An MCP server that exposes Prof. Null, an uncensored cybersecurity professor, as a set of specialized tools for learning hacking, CTFs, and security concepts through Q\&A, roadmaps, cheatsheets, labs, and more.
Exposes a pentest toolbox (sqlmap, nuclei, ffuf, etc.) via Docker to an LLM orchestrator for authorized security audits, with strict whitelisting and timeout controls.
Enables users to deterministically audit MCP servers for security issues across manifests, source, runtime responses, multi-call state, identity, and install scripts, and to run an inline gateway that gates tool calls and scans responses before returning them.
Exposes an OSINT investigation toolkit to any MCP-compatible AI client, which can drive passive checks such as DNS, WHOIS/RDAP, breach, IP reputation, GitHub and news-geo lookups and chain findings across them. The server lists 20 tools by default (16 passive plus 4 graph and batch helpers) and 25 when active checks are explicitly allowed, running via uvx with no separate install.
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.
Routes reverse-engineering requests by intent and target type (native binaries, Android apps, web/JS, Electron, .NET, firmware, protocols, archives, processes, UI, vulnerabilities) to the right analysis chain, orchestrating real backends such as Ghidra, JADX, apktool, adb, Frida, x64dbg, and pe-sieve with capability fallbacks and task-state tracking. Records evidence and claims in a ledger and applies three-layer verification (execution, fact, delivery), backed by an on-demand, book-style skill for guidance.
A read-only MCP server that lets an agent browse the HackerOne Hacker API using an authenticated hacker account, exposing programs, policies, scope, reports, and payments. It cannot create, update, or submit reports.
Enables AI assistants to search TryHackMe rooms and extract room overviews, task instructions, commands, and questions as clean Markdown for training and reference. Supports session-cookie authentication for subscriber content and includes curated foundational cybersecurity and Linux learning tracks.
Enables AI assistants to perform authorized WiFi security assessments, including network scanning, handshake capture, and password cracking, by executing aircrack-ng commands on a remote Kali Linux system via SSH.
Crash-tests your AI coding agent setup (Claude Code, Codex, Gemini CLI) against 20 traps modelled on real attacks, in a sealed container with fake keys, then hardens it. The MCP tools audit an agent's own setup locally and check its MCP servers against published vulnerabilities.
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.
Keeps bug-hunting AI agents within an authorized scope by checking every target against declarative allow/deny rules, refusing out-of-scope findings, and scrubbing secrets from evidence. It also computes CVSS v3.1 base scores and records findings in an append-only ledger.
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 AI agents to scan code for security vulnerabilities before execution, supporting Python and JavaScript/TypeScript with deterministic AST-based analysis and optional Solana micropayments.
Enables AI agents to interact with the FlagForge REST API, allowing them to search solved CTF challenges, work on live event challenges, record evidence, submit flag candidates, and write markdown writeups.
An MCP server for identifying SQL injection vulnerabilities in web applications using various techniques like error-based, time-based, and union-based scanning. It supports bulk URL processing, WAF bypass strategies, and authenticated testing across multiple database systems.
Enables AI assistants to execute security testing tools on a Kali Linux machine over SSH, including reconnaissance, web app scanning, and static/dynamic analysis.
Enables agents to inventory the Windows software installed on a machine and match it against current CVE sources (cvelistV5, CISA KEV, EPSS, NVD), turning the hits into a persistent to-do list prioritized by exploitation and severity. It also produces an AI effort assessment for each entry, either by sampling the client or by returning an evidence package the client writes back.
An intentionally vulnerable MCP server for security training, enabling users to practice attacking and defending AI agents through realistic scenarios.