Skip to content

MCP servers for security

576 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. Read-only-by-default tools for each Keycloak admin operation on a single realm

    Runs locally
    • Free
    • Security
  2. Self-hosted fleet of persistent, logged-in stealth Chrome sessions for AI agents

    Runs locally
    • Open source
    • Browser automation
  3. Grades any public GitHub repo A to F for safety, in plain English, before you install it

    Not checked yet
    • Remote
    • Free
    • Security
  4. Mac key vault where agents get scoped, expiring tokens and never the API keys

    Runs locally
    • 2 tools
    • Open source
    • Security
  5. Run live email deliverability checks, blacklists and spoofing grades from your AI

    Not checked yet
    • 4 tools
    • Remote
    • Free
    • Security
  6. Registry, scoped permissions and one-step recall for AI agents in health systems

    Not checked yet
    • Remote
    • Contact sales
    • Security
  7. Verify PDF signatures, detect tampering and get a trust verdict for incoming files

    Runs locally
    • 7 tools
    • Free
    • Files and documents
  8. Check IOCs and search threat reports, YARA rules, ATT&CK ids and CVEs on Rösti

    Not checked yet
    • 11 tools
    • Remote
    • Free
    • Security
  9. Scan prompts, tool definitions and model output for injection, and guard tool calls

    Runs locally
    • Open source
    • AI models and LLM tooling
  10. Passive-by-default OSINT lookups for AI agents: DNS, WHOIS, IP, breaches, Shodan and more

    Runs locally
    • 16 tools
    • Open source
    • Security
  11. Read EXIF, GPS, XMP, C2PA and AI-generator metadata from a public image or video URL

    Not checked yet
    • Remote
    • Free
    • Design and media
  12. Check whether a public MCP server's declared tools have changed since last seen

    Not checked yet
    • Remote
    • Free
    • Security
  13. Offline MCP scanner that inventories quantum-vulnerable cryptography in a code repository

    Runs locally
    • 1 tool
    • Free
    • Security
  14. Local security scanner that checks AI-written code and drives a scan, fix, rescan loop

    Runs locally
    • Open source
    • Security
  15. Persistent sandbox for coding agents: run commands, edit files, manage Git and sessions

    Not checked yet
    • 1 tool
    • Remote
    • Open source
    • Developer tools
  16. Free MCP server that checks PyPI and npm upgrades for vulnerabilities and breakage

    Not checked yet
    • 2 tools
    • Remote
    • Free
    • Developer tools
  17. Open-source MCP gate that signs an allow, deny or hold before each agent tool call

    Not checked yet
    • Remote
    • Open source
    • Security
  18. Public MCP honeypot that logs which AI agents and scanners touch its fake ops console

    Not checked yet
    • Remote
    • Free
    • Security
  19. Read-only CVE triage that explains each verdict from KEV, EPSS and exploit data

    Runs locally
    • 1 tool
    • Open source
    • Security
  20. Telegram MCP server with a separate key per AI client, scoped to chosen chats

    Runs locally
    • 18 tools
    • Open source
    • Communication
  21. Find leaked API keys and passwords in pasted text, flag live ones, and redact

    Not checked yet
    • 1 tool
    • Remote
    • Free
    • Security
  22. Read web malware techniques, kits and EtherHiding contracts from Ohey scans, no sign-in

    Not checked yet
    • 5 tools
    • Remote
    • Free
    • Security
  23. Search a curated directory of young security companies, with open stats under CC BY 4.0

    Not checked yet
    • 6 tools
    • Remote
    • Free
    • Security
  24. Free CVE lookup, dependency vulnerability checks and update feeds, no signup

    Not checked yet
    • 4 tools
    • Remote
    • Free
    • Security
  25. Signed, sealed handoffs between AI agents, with trust decided by the receiver

    Runs locally
    • Open source
    • Security
  26. Give an AI agent its own DID: prove identity offline, verify bundles, pay and message

    Not checked yet
    • 1 tool
    • Remote
    • Open source
    • Security

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