"Using npx to run tools directly without requiring an API" matching MCP servers:

Enables MCP-compatible AI applications to perform read-only npm package and project dependency safety scans, returning proceed, caution, or block verdicts without executing package code.

Enables AI agents to run passive, boundary, and gated active reconnaissance and web-security CLI tools (nmap, sqlmap, commix, httpx, ffuf, nikto, subfinder, and more) against authorized targets through a persistent, API-key-protected HTTP service. Scope gates, authorization windows, evidence capture, and a full audit trail are enforced in code so every tool call stays within the engagement's declared rules.

Enables MCP clients to invoke common Kali Linux pentesting tools directly as tool calls, with each binary executed safely without a shell.

Community MCP server for the Cymulate security validation platform. It exposes the full Cymulate REST API (337 endpoints) as 106 semantic tools for BAS, exposure validation, attack surface management, and platform administration.

Enables guardrail and trust testing by exposing realistic malicious tool patterns such as shell execution, credential dumping, and data exfiltration, all without network access.

Provides a disposable, hardened Kali Linux sandbox with an MCP interface for LLM-driven security analysis of REST APIs, confining blast radius via container isolation.

An MCP server that integrates various penetration testing tools, enabling security professionals to perform reconnaissance, vulnerability scanning, and API testing through natural language commands in compatible LLM clients like Claude Desktop.

Enables testing API authentication and authorization by probing endpoints with and without Authorization headers, suggesting auth test matrices for roles, and showing current test configuration.

Enables scanning OpenAPI specifications for security gaps and generating security test checklists for APIs.

Enables AI assistants to perform automated security audits on APIs, detecting BOLA/IDOR vulnerabilities by comparing responses across user tokens.

Scan-as-a-Service for MCP servers. Wraps the compuute-scan static security scanner with HTTP and MCP endpoints to analyze public GitHub repos for MCP-specific vulnerabilities.

Integrates 7 security tools (nmap, nuclei, dirsearch, sqlmap, hydra, Acunetix, Metasploit) via MCP protocol for AI-assisted penetration testing with enterprise-grade safety features.

Enables AI coding agents to audit websites for PHP runtime vulnerabilities, compile a live Zero-PHP Next.js App Router replacement preview from a WordPress/PHP site, and retrieve remediation guidance.

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 security teams to run controlled adversarial penetration tests against authorized ML/LLM API endpoints, scoring responses and generating evidence for compliance frameworks such as SOC 2, ISO 27001, and GDPR.

An MCP server that integrates multiple security and reconnaissance tools (Nmap, Cariddi, ParamSpider, Metasploit, web scraping) for AI systems, enabling automated network scanning, API discovery, vulnerability testing, and remote access via ngrok.

A production-ready HTTP API server for security testing and reconnaissance, integrating nmap, cariddi, paramspider, metasploit, and web scraping via FastAPI. It supports optional ngrok tunneling and exposes tools through REST endpoints.

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.

Provides security tools (prompt injection detection, CVE lookup, version impact assessment) for MCP clients like Claude.

Wraps Kali Linux penetration testing tools for authorized security assessments, driven by a local LLM via LM Studio.

Unified MCP server that gives AI agents security tools to audit MCP configs, redact secrets/PII, vet skills, check dependencies, and scan networks.

Integrates ProjectDiscovery security tools to perform automated reconnaissance, subdomain discovery, and vulnerability scanning. It enables comprehensive bug hunting workflows by chaining tools like subfinder, naabu, and nuclei into a unified pipeline.

Connects AI coding assistants to Snyk API & Web for onboarding scan targets, configuring authentication, running DAST scans, and triaging findings through natural language.

Provides multi-source vulnerability intelligence for AI-powered security operations, combining NVD CVSS, CISA KEV, and EPSS scores without requiring an API key.

Enables AI agents to generate audit reports and query financial ledger data via MCP. This demo version contains intentional security vulnerabilities for security testing and should not be used in production.

Provides access to 30+ Kali Linux penetration testing tools including Nmap, SQLmap, Metasploit, and others for authorized security testing, vulnerability scanning, and network reconnaissance through Claude Desktop.

Enables ethical security testing and attack surface management through SSL certificate validation, CVE queries, subdomain enumeration, security header analysis, and comprehensive reconnaissance capabilities. Designed for authorized penetration testing workflows with responsible disclosure practices.

Enables agents to inspect web pages for Cloudflare Turnstile challenges without an API key, and clear Turnstile or WAF challenges using a SolveGate API key.

Enables LLM agents to browse and triage vulnerability observations, manage products, branches and rules, import scan reports and SBOMs, run scans and background jobs, and generate VEX documents via SecObserve's REST API.

Connects AI assistants to Solodit's 49,000+ blockchain vulnerability database, enabling search, browse, and lookup of audit findings directly from your AI workflow.

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.

Enables searching and querying HackTricks pentesting documentation directly from Claude, with tools for quick lookup, grouped search results, page outlines, section extraction, and cheatsheet mode.

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.

MCP server that provides AI-native access to BeVigil's OSINT API, enabling mobile app security research and asset discovery through tools for hosts, subdomains, S3 buckets, URLs, wordlists, and multi-step investigations.

Exports vulnerability and asset data from Rapid7 Command Platform via the Bulk Export API into a local DuckDB database, enabling AI assistants to run natural language queries and SQL analysis with sandboxed security.

Enables passive security scanning of HAR files from QA test automation to detect missing security headers, insecure cookies, CORS misconfigurations, and leaked secrets, without making any live requests.

Connects MCP clients to pre-submission review that argues against a draft bug-bounty report or smart-contract finding the way a triager would, tying every claim to a supplied file and line and returning a submit, rewrite-then-submit, prove-first, hold-duplicate or drop verdict. Exposes tools to list review profiles, prepare reviews for the agent's own model, build hash-verified review packets, and — with a connection token — run hosted profiles on your own provider key.

GhostHunt is an MCP server that scans your development machine for API keys, tokens, and credentials hiding in places you forgot to check.

Enables any MCP client (Claude Code, Claude Desktop, Codex, or a custom agent) to fetch the latest CVEs at query time from live sources — NVD, CVE List V5, GitHub Advisory Database, CISA KEV and FIRST EPSS — without a separate API key. Exposes search, filtering (severity, RCE, PoC, KEV, keyword, CPE), per-CVE detail and risk-scored patch prioritization as JSON tools, so answers are grounded in live data rather than model memory.

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.