Skip to content

MCP servers for security

240 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. Scan Node.js projects for unprotected API routes and get an explained health score

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

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Finance and payments
  3. Self-hosted gateway that masks PII and signs receipts for AI access to your databases

    Runs locally
    • Open source
    • Security
  4. Record AI agent verdicts bound to file hashes and refuse stale ones before shipping

    Runs locally
    • Open source
    • Security
  5. Compare two logged-in identities to surface broken access control and IDOR

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

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

    Runs locally
    • 10 tools
    • Open source
    • Cloud and infrastructure
  8. Pay-per-call MCP check that rates an EVM address on Base as safe, caution or danger

    Runs locally
    • 7 tools
    • Paid
    • Security
  9. Docker-run MCP server for finding public emails and subdomains of a domain

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

    Runs locally
    • 3 tools
    • Open source
    • Security
  11. Open-source MCP server for IP, DNS, mail-auth and MCP endpoint checks

    Runs locally
    • 13 tools
    • Open source
    • Security
  12. Offline security scans for AI-written code: seven open-source scanners, one report

    Runs locally
    • Open source
    • Security
  13. Pins MCP tool definitions at approval and blocks the session when they change

    Runs locally
    • Open source
    • Security
  14. Collect API keys in a browser page and write them to .env without the model seeing them

    Runs locally
    • 1 tool
    • Open source
    • Security
  15. Wraps any MCP server so repeated write calls run once and every call is logged

    Runs locally
    • Open source
    • Developer tools
  16. Pay-per-call prompt-injection scanner that cleans pages before an agent reads them

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Security
  17. Secrets manager MCP server that runs commands with API keys the model never sees

    Runs locally
    • 2 tools
    • Open source
    • Security
  18. Structural code-quality scoring for coding agents, from SLOP to PLATINUM, run locally

    Runs locally
    • Open source
    • Developer tools
  19. Lets an agent buy short-term VPN and SOCKS5 proxy access by paying in USDC

    Runs locally
    • 3 tools
    • Paid
    • Security
  20. Open-source order limits, phone approval and a kill switch for trading AI agents

    Runs locally
    • Open source
    • Finance and payments
  21. Give a coding agent the dependency graph: scan, explain and diff packages

    Runs locally
    • 3 tools
    • Open source
    • Security
  22. Authorization proxy that needs a rule check and AI judges to approve each tool call

    Runs locally
    • Open source
    • Security
  23. Pay-per-call web reading, search, fact-checks and token screening for agents, in USDC

    Runs locally
    • 7 tools
    • Paid
    • Web search and scraping
  24. Lint Dockerfiles for root users, latest tags, secrets in ENV or ARG and more

    Runs locally
    • 3 tools
    • Open source
    • Developer tools
  25. Decode JWTs without trusting them, flag risky claims, verify signatures, mint test tokens

    Runs locally
    • 3 tools
    • Open source
    • Security
  26. Look up known vulnerabilities in OSV.dev by package and version, and scan lockfiles

    Runs locally
    • 4 tools
    • Open source
    • Security
  27. Grades a site's security headers and explains each one, over stdio

    Runs locally
    • 3 tools
    • Open source
    • Security
  28. Rules for each agent tool call, then a check of what a database really changed

    Runs locally
    • Open source
    • Security
  29. Score a domain's SPF, DMARC, DKIM and other email protections from your AI client

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Communication

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