Skip to content

MCP servers for security

392 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. Allow, deny or step-up checks on AI agent writes, with a tamper-evident log

    Runs locally
    • 10 tools
    • Freemium
    • Security
  2. MCP wrapper that holds database writes until a second person approves them on their phone

    Runs locally
    • Open source
    • Databases
  3. Free x402 preflight gate and paid on-chain checks before an agent signs a transaction

    Runs locally
    • 8 tools
    • Freemium
    • Security
  4. Gives coding agents your API keys without letting the model ever read them

    Runs locally
    • 4 tools
    • Open source
    • Security
  5. Read-only Trino access for agents, run as the verified user so Trino policy decides

    Runs locally
    • 3 tools
    • Open source
    • Databases
  6. Rank security scanner findings by exposure, criticality and exploitability

    Runs locally
    • Open source
    • Security
  7. Keep API keys in your OS keychain and give coding agents only what policy allows

    Runs locally
    • Open source
    • Security
  8. Let a coding agent connect repos, run vetkit audits and read findings and reports

    Runs locally
    • 4 tools
    • Freemium
    • Security
  9. Strip GPS, EXIF, C2PA and AI prompts from photos, video, PDFs and RAW files locally

    Runs locally
    • 2 tools
    • Open source
    • Security
  10. Local, reversible masking of client names and numbers before text goes to an AI

    Runs locally
    • Open source
    • Security
  11. Persistent, local-first memory for agents, stored as plain markdown

    Not checked yet
    • 11 tools
    • Remote
    • Freemium
    • Security
  12. Classify a signup email's domain as disposable, free, alias, test, parked or unknown

    • 3 tools
    • Remote
    • Freemium
    • Security
  13. Verify who controls a phone, email or domain, and get signed human approvals

    • 200 tools
    • Remote
    • Freemium
    • Security
  14. Open-source MCP gateway that pins tools, holds risky calls and limits egress

    Runs locally
    • Open source
    • Security
  15. Open-source MCP server scoring pull-request risk from blast radius and git history

    Runs locally
    • 4 tools
    • Open source
    • Developer tools
  16. Open-source control plane that firewalls MCP tool calls and caps agent model spend

    • Remote
    • Open source
    • Security
  17. Policy-gated agent spending with signed receipts and audit against the payment rail

    Runs locally
    • 5 tools
    • Open source
    • Finance and payments
  18. Rate nudity in images, GIFs and videos from 0 to 3 with a blocked or allowed verdict

    • 3 tools
    • Remote
    • Freemium
    • Security
  19. MSP-focused MCP server and CLI for WatchGuard Cloud across customers

    Runs locally
    • Open source
    • Security
  20. Screen a USDC payee for lookalike, reserved or self-addresses before an agent sends funds

    Runs locally
    • Freemium
    • Finance and payments
  21. Lint Dockerfiles and Kubernetes manifests for an A-F grade and a fix per finding

    Runs locally
    • 1 tool
    • Freemium
    • Developer tools
  22. Read-only payment preflight for AI agents: pay, review or do-not-pay before signing

    • 9 tools
    • Remote
    • Open source
    • Security
  23. Checks JS/TS written by AI for risky patterns, fake npm packages and weakened tests

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  24. Look up whether an IP address is a VPN, proxy, Tor node, hosting range or CDN

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Security
  25. IP, ASN and domain data for AI agents: location, ownership, anonymity and open services

    Not checked yet
    • Remote
    • Freemium
    • Analytics and data
  26. Free pre-payment checks for agents: sanctions and AML screening of payees and requests

    • 13 tools
    • Remote
    • Freemium
    • Security
  27. Run an 88-test MCP spec compliance suite and get an A-F grade from CLI or agent

    Runs locally
    • 2 tools
    • Open source
    • Security

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