DirectoryMCP servers

Security: mcp servers in 2026

14 entries, ranked by their latest verification, share of daily checks passed, sourced facts and response time. Never by payment.

1. Verity Verified working on 2026-10-27 · #1 in Security
   Cited product-compliance ground truth for AI agents. Never generates; always cites.
2. tech-risk Verified working on 2026-10-27 · #2 in Security
   MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/08) + Base data
3. VerifyPulse Email Verification & DNS Security Verified working on 2026-10-27 · #3 in Security
   Real-time RFC 5322 email verification, SPF/DMARC DNS audits & B2B leads (x402 Base USDC).
4. sectora Verified working on 2026-10-27 · #4 in Security
   Threat intel + your scans/findings/Shield posture. CVE, EPSS, KEV, package vuln lookup, DAST.
5. MCP Marketplace Verified working on 2026-10-27 · #5 in Security
   Search and install 4,000+ security-scanned MCP servers from inside any MCP-aware AI client.
6. Toolcall Verified working on 2026-10-27 · #6 in Security
   30 pay-per-call APIs for AI agents: compliance, trade, safety, web, data. USDC on Base via x402.
7. VITNA – Containment for rogue AI agents Verified working on 2026-10-27 · #7 in Security
   Guard wraps stdio MCP servers: risky calls wait for a person; no answer, no run. Remote: cooperative
8. Electronic Compliance Objects (49 markets) Verified working on 2026-10-27 · #8 in Security
   Each market's disclosure regime as one sourced, signed object, with the issuer's ACM-68000 signal.
9. HoneyLabs Verified working on 2026-10-27 · #9 in Security
   Honeypot probe data: IP reputation, scanners, CVE probing, TLS and SSH fingerprints.
10. KarmaDue Verified working on 2026-10-27 · #10 in Security
    Pre-install safety check for agents: known traps, tested fixes, malware reports. No account.
11. gateway Reachable on 2026-10-27: sign-in required, tools not listed · #11 in Security
    MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
12. kanonik Reachable on 2026-10-27: sign-in required, tools not listed · #12 in Security
    Governance runtime for compliance: verified, human-approved writes to a tamper-evident record.
13. mlab.sh Reachable on 2026-10-27: sign-in required, tools not listed · #13 in Security
    Threat intelligence: enrich IOCs (IP, domain, URL, hash), search CVEs and actors, scan SBOMs.
14. TAP Reachable on 2026-10-27: sign-in required, tools not listed · #14 in Security
    Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.

Ranking rule and methodology · Markdown