Security MCP servers

Real-device ad verification: malvertising and cloaking scans, AI policies, alerts, webhooks.

Manage Koru Shield DNS filtering: profiles, rules, categories, schedules, and logs.

Guard AI agents' PostgreSQL/MySQL access via MCP: SQL audit, auth, masking, write approval

Control plane for agent auth walls. Connector 0 handles SMS OTP with US test numbers.

Discover exposed assets, leaked secrets, APIs & client-side vulns across your attack surface

Ask your security cameras anything and set up alert rules in a sentence. Built into Agent DVR.

Identity and authorization in one system: allow, deny, the reason, and a record.

PentaTrail ASM/CTEM: attack surface discovery, asset inventory, findings by threat level

KYC verification on autopilot for Bybit, MEXC and Bitget. 150 countries, pay per result.

Verify photos are real camera captures, not AI: C2PA and RAW+JPEG forensics. OAuth or API key.

Defensive vulnerability intelligence search across public CVE/NVD and GitHub advisory APIs with CVSS

Defensive Shodan search and host intelligence MCP using customer-provided SHODAN_API_KEY for

Fallax is a phishing simulation and security awareness training platform. Read your results.

List, schedule, and retrieve evidence for ControlDrill incident-response tabletop exercises.

UNVERIFIED: cross-cloud beta; sandbox by default; production opt-in via customer Guardian.

Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.

Enrich, search, assess, and manage threat intelligence through 80+ typed MCP tools.

Query Truss threat intelligence via hosted MCP (OAuth). Growth+ plans.

Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.

The first MCP governed by ICA. Every action is gated and sealed with a verifiable receipt.

MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.

CVE intelligence, STRIDE, OWASP test cases via Ansvar Gateway. Cited, OAuth + paid.

Crypto transaction firewall and risk tools for MCP agents.

Browser QA agent that won't return a false green: verified PASS/FAIL + access-control probing.

Identity, secrets, and passwordless SSH provisioning for AI agents — Keycloak, vault, MCP tools.

Sovereign MCP Gateway — 64 governed tools with Merkle transparency log. EU AI Act ready.

Find relevant security data from Sentinel data lake for building effective agents. More:aka.ms/s/de

Agent tools: web fetch/extract, site checks, domains, email, dep scans. Spending needs a passkey.