Security & Testing MCP Servers for Claude Desktop

MCP server that exposes browser accessibility tree via Chrome CDP

A transparent MCP proxy that intercepts dangerous tool calls and requires OTP-based user approval.

MCP server for AI agent safety — cost guards, injection scanning, decision tracing, agent identity (KYA), and signed receipts

Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded

Lightweight dependency vulnerability audit tool with CLI and MCP Server support

MCP server for AuditSpark — audit any website from Claude. Scores SEO, performance, accessibility, UX, content, and 10+ other categories in

Official MCP server for Autousers — UX evaluation, calibrated AI personas, side-by-side design review.

Model Context Protocol server for DNS and email security scanning using basicsec

MCP server for BBOT security scanner

MCP server for Beaker lab automation — system provisioning, job management, distro discovery, and failure diagnosis

Unified MCP server for Bind Protocol — credential tools, API gateway, and action receipts for AI agents

Verify an EVM chainId or RPC endpoint is legit (not spoofed): identity + live eth_chainId/net_version probe. VERIFIED/CAUTION/MISMATCH. MCP

Live CORS misconfiguration probe: origin reflection, wildcard+credentials, null-origin, substring bypass. SAFE/RISKY/DANGEROUS. MCP + x402.

MCP server for ctscout.dev — domain attribution via Certificate Transparency + multi-signal Pro enrichment

Autonomous security scanner for AI agents. Detects prompt injection, tool abuse, data exfiltration, and OWASP ASI Top 10 vulnerabilities.

MCP server for domain intelligence — DNS records, WHOIS lookups, SSL certificate checks, and domain availability

Redact EU personal data (names, national IDs, IBANs) in text and files; restore it later.

Fagun — one MCP server that lets any AI tool (Claude, Cursor, Codex, Antigravity, Windsurf) use a site as real end users, run full UAT

Model Context Protocol server exposing Fracta scan tools (passive_scan, scan_repo, …)

MCP (Model Context Protocol) server for glin-profanity - enables AI assistants like Claude, Cursor, and others to use profanity detection

Detecta e mascara dado pessoal brasileiro (CPF, CNPJ, RG, e-mail) antes do texto ir a uma IA. LGPD.