Skip to content

MCP servers for security

575 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 Trino access for agents, run as the verified user so Trino policy decides

    Runs locally
    • 3 tools
    • Open source
    • Databases
  2. Check a store or product page for scam and dark-pattern signals before buying

    Runs locally
    • 2 tools
    • Paid
    • E-commerce
  3. Rank security scanner findings by exposure, criticality and exploitability

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

    Runs locally
    • Open source
    • Security
  5. Local anonymiser that swaps client names and amounts for codes before Claude reads files

    Runs locally
    • Free trial
    • Security
  6. Let a coding agent connect repos, run vetkit audits and read findings and reports

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

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

    Runs locally
    • Open source
    • Security
  9. Keyless CVE, KEV, EPSS and advisory lookups with per-CVE internet exposure counts

    • 16 tools
    • Remote
    • Free
    • Security
  10. Verify who controls a phone, email or domain, and get signed human approvals

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

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

    Runs locally
    • 4 tools
    • Open source
    • Developer tools
  13. Policy-gated agent spending with signed receipts and audit against the payment rail

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

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

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

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

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

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

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

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Security
  21. Agents use your API keys, SSH keys and wallets via a local broker and never hold them

    Runs locally
    • 10 tools
    • Free
    • Security
  22. IP, ASN and domain data for AI agents: location, ownership, anonymity and open services

    Not checked yet
    • Remote
    • Freemium
    • Analytics and data
  23. Give each AI agent its own inbox, saved logins and 2FA codes

    • Remote
    • Free trial
    • Security
  24. Free pre-payment checks for agents: sanctions and AML screening of payees and requests

    • 13 tools
    • Remote
    • Freemium
    • Security
  25. 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
  26. Local input firewall that scans text, files and MCP metadata for prompt injection

    Runs locally
    • Open source
    • Security
  27. Sealed microVM sandboxes for agents to run untrusted code, locally or in the cloud

    Not checked yet
    • Remote
    • Free trial
    • Developer tools
  28. Electron IPC scaffolding, security audits, CSP and build-error diagnosis for assistants

    Runs locally
    • 8 tools
    • Open source
    • Developer tools

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