Skip to content

MCP servers for security

567 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. Inspect and manage a UniFi network: devices, clients, WiFi, firewall and VPN

    Runs locally
    • Open source
    • Cloud and infrastructure
  2. Pay-per-call agent tools over x402: token safety checks, speech, OCR, translation

    Not checked yet
    • 17 tools
    • Remote
    • Paid
    • Design and media
  3. Manage and secure MCP servers on Speakeasy's AI control plane from an agent

    Not checked yet
    • Remote
    • Paid
    • Security
  4. Self-hosted OWASP ZAP operator that lets AI agents run guided security scans and reports

    Not checked yet
    • Remote
    • Open source
    • Security
  5. Pre-payment safety checks for AI agents on Base, with a free SpendGuard policy tool

    Not checked yet
    • 7 tools
    • Remote
    • Paid
    • Finance and payments
  6. Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents

    Not checked yet
    • 2 tools
    • Remote
    • Open source
    • Security
  7. Scan, fix and justify container builds with an authorization console for the cDSO pipeline

    Not checked yet
    • 13 tools
    • Remote
    • Paid
    • Security
  8. Pay-per-call x402 attestations, bounty-packet preflight and read-only Base and DNS checks

    Not checked yet
    • 6 tools
    • Remote
    • Paid
    • Finance and payments
  9. Pay-per-call risk screen for tokens on Base: rug pulls, honeypots and copycats

    Not checked yet
    • 2 tools
    • Remote
    • Paid
    • Security
  10. Secret broker that injects credentials at the point of use, never into the model

    Runs locally
    • Open source
    • Security
  11. Launch check for AI-built web apps with a SAFE or DO NOT SHIP verdict and fixes

    Not checked yet
    • Remote
    • Paid
    • Security
  12. Hosted MCP server that timestamps file hashes in Bitcoin, paid per hash with x402

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Security
  13. Crypto address screening for agents: sanctions, stablecoin blacklists and scam lists

    Not checked yet
    • Remote
    • Paid
    • Finance and payments
  14. Pay-per-call OT and ICS threat intelligence for agents, settled in USDC via x402

    Not checked yet
    • Remote
    • Paid
    • Security
  15. Local vault MCP server that lets agents use API keys without ever seeing them

    Runs locally
    • 1 tool
    • Paid
    • Security
  16. Open forum and end-to-end encrypted direct messages for AI agents, keys held client-side

    Runs locally
    • Open source
    • Communication
  17. Ask an action firewall for an allow, review or block verdict before an agent acts

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Security
  18. Local npm package that gates agent actions with allow, review or block verdicts

    Runs locally
    • 4 tools
    • Paid
    • Security
  19. Journal, approve or block, and sandbox every MCP tool call your AI agent makes

    Runs locally
    • Open source
    • Security
  20. Local static audit of AI model files with hash-bound evidence for deployment reviews

    Not checked yet
    • Remote
    • Open source
    • AI models and LLM tooling
  21. Manage SimpleLogin aliases, mailboxes, domains and settings from an MCP client

    Runs locally
    • 14 tools
    • Open source
    • Security
  22. Manage Ghost Networks private mesh networks, hubs, VPN and devices from your AI client

    Runs locally
    • Paid
    • Cloud and infrastructure
  23. Pay-per-call DNS, WHOIS, TLS and blocklist checks for agents and developers

    Not checked yet
    • 23 tools
    • Remote
    • Paid
    • Security
  24. One-call risk verdict for Base ERC-20 tokens: rug-pull signals, holders and momentum

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Finance and payments
  25. Read-only MCP server for triaging EyalSec Python security events from an assistant

    Runs locally
    • 3 tools
    • Paid
    • Security
  26. Open-source MCP proxy that enforces policies, budgets and approvals on agent tool calls

    Not checked yet
    • Remote
    • Open source
    • Security

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