Security MCP servers

Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).

Govern your backend control plane from your AI agent - signed, human-approval-gated.

Live honeypot threat intel: attacker IPs, IOCs, credentials, payloads, actors.

DEPRECATED: no live endpoint (api.unico.co does not resolve)

Detect any website's tech stack, security headers, SSL, DNS and CVEs via DetectZeStack.

Open standard MCP server for Zero-Trust Data Sanitization (ZTDS RFC v1.0). In-memory PII masking.

CVE checks, supply chain signals, live catalog, and CVE detail for MCP clients (infra, PyPI, npm).

13 rules that decide whether a vulnerability report ever reaches you

Pre-install security scanner for AI agent skills (local stdio MCP). Offline static scan; no upload.

Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.

AI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints

MCP server for SecObserve: triage findings, import scan reports and SBOMs, generate VEX.

Jev judgments for agents: injection scanning, shell risk gating, ranking

MCP server for LenelS2 S2 NetBox access control via the NBAPI. Read-only by default.

Paid x402 facts for AI agents: signed statements, door reports, endpoint checks, chain reads

MCP server for OneLogin API - manage users, apps, roles, and authentication

CyberChef's 504 data-transformation operations as MCP tools: encryption, encoding, forensics.

Local MCP proxy for tool restrictions, response redaction, audit logs, and database schema context.

Catches hallucinated and slopsquatted npm and PyPI packages before an agent installs them.

MCP policy proxy: enforces a code of conduct across connectors before the upstream is called.

Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.

AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.

Audit Solidity and Rust smart contracts from your editor. Pays per audit in USDC over x402.

Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.

Free passive security scanning - check any domain's DMARC, TLS, headers, and exposures.

Wrap any MCP server with enforced, bounded, revocable permissions — grant, narrow, check, revoke.

Verifies a merchant storefront is legitimate before an AI agent commits payment.

Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.