Skip to content

MCP servers for security

407 MCP servers that scan for vulnerabilities, manage secrets and investigate threats. Each one shows how to install it in Claude, Cursor and VS Code, whether it runs locally or remotely, and the tools it provides.
  1. On-premises document retrieval for agents, with folder-level access rules checked first

    Runs locally
    • Open source
    • Knowledge and memory
  2. Read-only npm preflight: reviews what install scripts do before packages run

    Runs locally
    • Open source
    • Security
  3. MCP server that checks if a video is AI-generated, scoring picture and sound separately

    Not checked yet
    • 4 tools
    • Remote
    • Free trial
    • Design and media
  4. OWASP API Top 10 tests from your OpenAPI spec, plus scanner SARIF judged for release.

    Runs locally
    • Open source
    • Security
  5. Tamper-evident local record of what your AI agent did, plus verifiable markdown memory

    Runs locally
    • 9 tools
    • Open source
    • Knowledge and memory
  6. Guard agents' PostgreSQL and MySQL access with SQL audit, masking and write approval

    Not checked yet
    • Remote
    • Open source
    • Databases
  7. Role-aware onboarding answers about a codebase, filtered to what the caller may see

    Not checked yet
    • 9 tools
    • Remote
    • Open source
    • Developer tools
  8. Find and strip zero-width, bidi and tag characters hidden in text, offline

    Runs locally
    • 5 tools
    • Open source
    • Security
  9. Check an agent work row, post one and preflight a no-spend cap before spending

    Runs locally
    • 11 tools
    • Open source
    • Developer tools
  10. Access control for AI agents: allow, hold for approval or block each tool call

    Runs locally
    • Open source
    • Security
  11. CNCF release intelligence: typed changes from release notes and local stack checks

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  12. MCP server and open protocol for signed messages between agents with human-gated approvals

    Runs locally
    • Open source
    • Developer tools
  13. Signed, hash-chained receipts of agent tool-call decisions, verifiable offline

    Runs locally
    • Open source
    • Security
  14. Vulnerability management across all ConnectSecure clients: exposure ranking, CVE impact…

    Runs locally
    • Open source
    • Security
  15. Abnormal Security email threats, cases, and reporting in your terminal and your AI agents.

    Runs locally
    • Open source
    • Security
  16. Hook Security phishing and training data for MSPs: click rates, overdue training, QBR…

    Runs locally
    • Open source
    • Security
  17. Read-only Keeper MSP posture across every client, with history, a change feed and no…

    Runs locally
    • Open source
    • Security
  18. Fraud and abuse investigation, escalation triage and rule tuning inside Dregs

    Not checked yet
    • 2 tools
    • Remote
    • Free trial
    • Security
  19. VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP…

    Runs locally
    • Open source
    • Security
  20. Zero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack…

    Runs locally
    • Open source
    • Security
  21. Local checks for Unicode confusables, mixed scripts, invisible controls, and suspicious…

    Runs locally
    • Open source
    • Security
  22. Security controls, evidence, risk and vendor management for the open SCF Controls Platform

    Runs locally
    • 9 tools
    • Open source
    • Security
  23. CIRCL Vulnerability-Lookup — aggregated vulnerability records

    Not checked yet
    • Remote
    • Open source
    • Security
  24. Offline methodology engine for authorized penetration testing, CTF, and security research.

    Not checked yet
    • Remote
    • Open source
    • Security
  25. CVE Search: latest CVEs and vendor or product lookups from CIRCL - keyless.

    Runs locally
    • Open source
    • Security
  26. MCP server for OSV open source vulnerability data and package security checks.

    Runs locally
    • Open source
    • Security
  27. Detect hardcoded secrets in source and config. Reports masked previews, never the values.

    Runs locally
    • Open source
    • Security

See every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.