Skip to content

MCP servers for security

603 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. Open-source gateway that routes AI requests by privacy policy and governs tool access

    Not checked yet
    • Remote
    • Open source
    • Knowledge and memory
  2. Python library that adds permission tiers, approval gates and audit logs to MCP servers

    Runs locally
    • Open source
    • Security
  3. Rust reverse-engineering MCP server that returns evidence-backed findings on binaries

    Runs locally
    • Open source
    • Security
  4. File ownership, expiring shares and audit trail for SaaS apps, exposed to agents over MCP

    Runs locally
    • Open source
    • Files and documents
  5. Open-source evidence lake that grades security controls for audits

    Runs locally
    • Open source
    • Security
  6. Pay-per-call package vulnerability lookups and manifest audits over x402

    Not checked yet
    • 5 tools
    • Remote
    • Paid
    • Security
  7. Screens messages and links for scam patterns in English and Spanish with offline rules

    Not checked yet
    • Remote
    • Paid
    • Security
  8. Email MCP server for Gmail, Outlook and IMAP that fences messages against prompt injection

    Runs locally
    • 12 tools
    • Open source
    • Communication
  9. Passive scan of a website's AI-agent readiness: robots, llms.txt, JSON-LD, MCP, security

    Runs locally
    • Open source
    • Marketing and SEO
  10. Give an AI assistant its own Bitwarden vault for logins, 2FA codes and passkeys

    Runs locally
    • 7 tools
    • Open source
    • Security
  11. Run untrusted agent shell commands in a gVisor sandbox from any MCP client

    Runs locally
    • 1 tool
    • Open source
    • Security
  12. Scan Node.js projects for unprotected API routes and get an explained health score

    Runs locally
    • Open source
    • Developer tools
  13. Pay-per-call SAFE, CAUTION or DANGER verdicts for new ERC-20 tokens on Base

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Finance and payments
  14. Rule-based scans for prompt injection, poisoned MCP tools and unsafe x402 endpoints

    Not checked yet
    • 5 tools
    • Remote
    • Paid
    • Security
  15. Self-hosted gateway that masks PII and signs receipts for AI access to your databases

    Runs locally
    • Open source
    • Security
  16. Preflight trust check for x402 payment endpoints, with an ok, caution or avoid verdict

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Finance and payments
  17. Record AI agent verdicts bound to file hashes and refuse stale ones before shipping

    Runs locally
    • Open source
    • Security
  18. Signed, chain-anchored receipts that prove which model said what and when

    Runs locally
    • 6 tools
    • Paid
    • Security
  19. Manage Pi-hole v6 DNS blocking, domains, clients, DHCP and query logs from an assistant

    Runs locally
    • 10 tools
    • Open source
    • Cloud and infrastructure
  20. Compare two logged-in identities to surface broken access control and IDOR

    Runs locally
    • Open source
    • Security
  21. Remote MCP server for your monitored domains: DNS, email security, changes and deep scans

    Not checked yet
    • 24 tools
    • Remote
    • Paid
    • Security
  22. Docker-run MCP server for finding public emails and subdomains of a domain

    Runs locally
    • 4 tools
    • Open source
    • Security
  23. Docker-run MCP server that identifies the CMS, server and frameworks behind a website

    Runs locally
    • 3 tools
    • Open source
    • Security
  24. 29 deterministic audits for APIs, CI, containers and web files, paid per call

    Not checked yet
    • Remote
    • Paid
    • Developer tools

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