Skip to content

MCP servers for security

583 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. Local vault MCP server that lets agents use API keys without ever seeing them

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

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

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

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

    Runs locally
    • Open source
    • Security
  6. 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
  7. Manage SimpleLogin aliases, mailboxes, domains and settings from an MCP client

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

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

    Not checked yet
    • 23 tools
    • Remote
    • Paid
    • Security
  10. 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
  11. Read-only MCP server for triaging EyalSec Python security events from an assistant

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

    Not checked yet
    • Remote
    • Open source
    • Security
  13. Verify blockchain timestamp proofs offline and anchor file hashes through ProofLedger

    Runs locally
    • Open source
    • Security
  14. Policy-check every x402 paywall an AI agent meets before any payment moves

    Runs locally
    • Open source
    • Finance and payments
  15. Typed, policy-checked server operations for AI agents, with approvals and an audit log

    Runs locally
    • 11 tools
    • Open source
    • Developer tools
  16. Pay-per-call audit of a site's security headers, TLS setup and cookies for AI agents

    Not checked yet
    • 2 tools
    • Remote
    • Paid
    • Security
  17. Read-only graph tools for cross-bank money-laundering cases, with Cypher for each claim

    Not checked yet
    • 12 tools
    • Remote
    • Open source
    • Finance and payments
  18. MCP server to validate Guard Core SecurityConfig, search its docs and check threats

    Runs locally
    • Open source
    • Security
  19. Quote and build HITZ, XLM and USDC swaps on Stellar's Sovereign Vault for AI agents

    Not checked yet
    • 6 tools
    • Remote
    • Open source
    • Security
  20. Local checks for sudo, systemd, sshd, ufw and secret leaks before an agent runs commands

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  21. Counterparty compliance verdicts that AI agents can buy per call before paying

    Not checked yet
    • Remote
    • Paid
    • Security
  22. Pay-per-call rug checks for Solana tokens that return SAFE, CAUTION or DANGER

    Not checked yet
    • Remote
    • Paid
    • Security
  23. AI pre-audit scanner for Solidity, Cairo and Rust smart contracts, usable from MCP clients

    Not checked yet
    • 8 tools
    • Remote
    • Paid
    • Security
  24. Known OSV vulnerabilities and fixed versions for up to 50 exact package versions

    Not checked yet
    • 1 tool
    • Remote
    • Paid
    • Security
  25. CNCF release notes turned into typed changes, with a local stack version check

    Runs locally
    • 1 tool
    • Open source
    • Cloud and infrastructure
  26. Pay-per-call domain checks: TLS, DNS, email auth, security headers and threat lookups

    Not checked yet
    • 5 tools
    • Remote
    • Paid
    • Security

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