Security MCP servers

MCP server for RouteVerdict — x402 endpoint trust checks ($0.05 USDC on Base)

Provision, ship, and pay from your coding agent — keys and cards never leave the vault.

Check an AI-built app is safe to launch, then deploy it on accounts you own.

Maps every service that sends email as a domain, with the public record behind each one.

Local security scanner for AI agents: SAST, SCA, secrets, IaC; verifies exploit and fix.

Confirmed vulnerabilities and exposure for IPs, domains and software versions (NVD, CISA KEV, EPSS)

Read-only attack-path tools: reachable routes to sensitive assets, and what a fix would cut.

Append-only evidence receipts for AI records: seal, verify, cite, chain-check, anchor status.

Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.

Check Proof of Process chains: record, file match, timestamps, registry. Never one verdict.

Sourced, evidence-aware CVE research for CVEs, products, SBOMs and images via NVD, EPSS, KEV, OSV.

Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.

Security scanner for AI-generated code. 30 free rules; all 223 with a paid-plan API key.

Find leaks in AI-built apps: open Supabase/Firebase data, exposed keys, unsafe edge functions

Connects AI agents with CrowdStrike Falcon for security analysis and automation.

Check finite candidate proposals against separate policy and evidence, with canonical hash receipts.

Standalone launcher and agent integration for the PT Application Inspector MCP proxy.

Local secret guardrails: scan code, git changes and MCP configs for API keys; redact text

Query IP locations and network ownership in GeoIP2, GeoLite2, and custom MMDB databases.

MCP server for Cyberbro IOC extraction, enrichment and reputation analysis.

Assess a domain, IP or ASN: mail and DNS security, certificates, routing and a report card.

REA reverse-engineering MCP server in Docker, with JADX, Apktool and adb for APKs.

Team secrets your AI agent can use but never read: encrypted in the repo, value-blind tools.

Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.

VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.

Pin MCP tool contracts by sha-256; catch silent drift, rug pulls and bait-and-switch in CI.

Local MCP broker: agents call credentials through a daemon without seeing secrets.

Audit a domain's email and web security: SPF, DKIM, DMARC, MTA-STS, DNSSEC, TLS, WHOIS. No API keys.