Security & Testing MCP Servers for Perplexity

Line-by-line check of shipped device defaults against RED Art. 3(3)(d)(e)(f), EN 18031-1/-2/-3 and U

Domain security scanning for AI agents. A-F grades, 8 checks, fix snippets.

Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.

One-call trust check for any domain (A0-A4, verdict, signed) + fact passports; same tools as remote

Checks a Markdown folder's OKF frontmatter tier, locally. No-egress is a vendor claim: see README.

MEOK Enterprise Compliance Checker — EU AI Act, DORA, GDPR automated gap analysis. £5K-15K audits

MEOK MCP Hardening MCP — automated security red-team for any MCP server. Maps OWASP LLM Top 10 (2025) + 5 MCP-specific risks to a 0-100

Norwegian government cybersecurity standards MCP -- 19 frameworks, 524 controls. NSM (ICT, physical, governance, technical measures, encrypt

Query Microsoft Patch Tuesday security updates (MSRC) with EPSS and CISA KEV enrichment

Supply chain security risk scorer for npm, PyPI, Cargo, and Go packages — behavioral signals that can't be faked

MCP server for Metasploit Framework via pymetasploit3

Deterministic, zero-token security scanner your AI agent calls to find and re-verify issues.

Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.

MCP server for AI agents to interact with The Agent Cafe — an on-chain restaurant on Base where agents buy food tokens and receive gas

MCP servers for AgentLedger — user agent and supervisor agent

Verify signed ALEX Evidence Packages. Fails closed on signature or schema errors.

A lightweight MCP security guard for Claude Code users and indie AI builders. A pre-connection MCP security diagnostic tool for Claude Code

Chrome Enterprise Premium MCP server

MCP server for ClassiFinder — secret scanning tools for AI agents

Structural similarity-based code filter. Stops malicious code pattern reaching execution tools.

Signs, hash-chains, and verifies compute usage receipts via an MCP server, no issuer trust required.