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. Read-only scanner that checks remote MCP servers for tool poisoning and silent changes

    Not checked yet
    • Remote
    • Paid
    • Security
  2. Turns web pages and PDFs into clean Markdown and strips hidden prompt-injection text

    Not checked yet
    • Remote
    • Paid
    • Web search and scraping
  3. Local MCP server for invisible watermarking and detection of images, PDFs and video

    Runs locally
    • 28 tools
    • Free trial
    • Design and media
  4. Authorization proxy that needs a rule check and AI judges to approve each tool call

    Runs locally
    • Open source
    • Security
  5. Checks a transaction, typed data or text before an agent wallet signs, $0.01 a check

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Security
  6. Pay-per-call web reading, search, fact-checks and token screening for agents, in USDC

    Runs locally
    • 7 tools
    • Paid
    • Web search and scraping
  7. Free signed check of an x402 paid endpoint, run by an agent before it pays

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  8. Screen people and companies against sanctions lists and fetch the audit record

    Runs locally
    • 1 tool
    • Free trial
    • Security
  9. Find B2B buyers with a live reason to talk and run LinkedIn outreach from your own Claude

    Not checked yet
    • Remote
    • Paid
    • Sales and CRM
  10. Lint Dockerfiles for root users, latest tags, secrets in ENV or ARG and more

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

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

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

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

    Runs locally
    • Open source
    • Security
  15. 70 pay-per-call utility APIs for DNS, security checks, text, scraping and AI work

    Not checked yet
    • 8 tools
    • Remote
    • Paid
    • Web search and scraping
  16. Self-hosted gateway that lets AI agents use your accounts, with writes held for approval

    Not checked yet
    • Remote
    • Open source
    • Security
  17. Timestamp a file's SHA-256 fingerprint on BitcoinZ with shielded zk-SNARK proofs

    Not checked yet
    • 3 tools
    • Remote
    • Free trial
    • Security
  18. Search, price and buy agent-ops templates and security kits by Stripe checkout

    Not checked yet
    • Remote
    • Paid
    • Security
  19. Score a domain's SPF, DMARC, DKIM and other email protections from your AI client

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Communication
  20. RFC 3161 timestamp receipts and a signed agent ledger, paid per call over x402

    Not checked yet
    • 14 tools
    • Remote
    • Paid
    • Security
  21. Check a website's post-quantum readiness and read internet-wide adoption figures

    Runs locally
    • 5 tools
    • Open source
    • Security
  22. Adopt, read, verify and record an Open Entity identity for an AI agent, no auth

    Not checked yet
    • 6 tools
    • Remote
    • Open source
    • Security
  23. Drafts a network allow list for an agent tool and test-runs it with the network blocked

    Runs locally
    • 3 tools
    • Open source
    • Security
  24. Scores and seals AI decisions into a Bitcoin-timestamped audit chain for compliance checks

    Not checked yet
    • Remote
    • Free trial
    • Finance and payments
  25. Let agents use and save 1Password secrets locally without ever seeing the plaintext

    Runs locally
    • Open source
    • Security
  26. Green, orange or red verdicts on transactions, permits and tokens before an agent signs

    Not checked yet
    • 2 tools
    • Remote
    • Paid
    • Security
  27. Check an npm or PyPI package's Attestari grade before an agent installs it

    Not checked yet
    • Remote
    • Free trial
    • Security

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