Skip to content

MCP servers for security

199 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. Check an agent's payment entitlement and get signed spending-policy preflights

    Runs locally
    • 3 tools
    • Freemium
    • Finance and payments
  2. MCP server that gives AI agents real inboxes with send, receive and injection scanning

    Not checked yet
    • Remote
    • Freemium
    • Communication
  3. Pay-per-call checks for agents: packages, CVEs, legal citations and transactions

    Runs locally
    • Paid
    • Security
  4. Lets coding agents sign in and run commands without ever seeing passwords or 2FA codes

    Runs locally
    • 5 tools
    • Freemium
    • Security
  5. Escrow, spend limits and reputation checks for AI agents paying over x402 on Base

    Not checked yet
    • 3 tools
    • Remote
    • Freemium
    • Finance and payments
  6. Pins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets

    Runs locally
    • 2 tools
    • Open source
    • Security
  7. Check an npm or PyPI package for advisories and typosquats before you install it

    Runs locally
    • 1 tool
    • Freemium
    • Security
  8. Score a service's terms of service for risk before your agent accepts them

    Runs locally
    • 1 tool
    • Freemium
    • Legal and government
  9. Grade a URL like an attacker would, scan repos and check Supabase, Stripe and Vercel

    Runs locally
    • 2 tools
    • Freemium
    • Security
  10. Masks Brazilian CPF, CNPJ and other personal data in text before it reaches an AI

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  11. Scan a deployed site for an exposed Supabase service_role key and audit its RLS

    Runs locally
    • 10 tools
    • Open source
    • Security
  12. Pass, fail or review verdicts and a recommended action for LLM output

    Not checked yet
    • 13 tools
    • Remote
    • Freemium
    • AI models and LLM tooling
  13. Local ACT, BLOCK or ESCALATE check that runs before an AI agent takes an action

    Runs locally
    • 1 tool
    • Open source
    • Security
  14. Read-only library of 24 defensive security skills served over MCP

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  15. Send and verify one-time passcodes by SMS, WhatsApp and Telegram from an agent

    Not checked yet
    • 10 tools
    • Remote
    • Free trial
    • Communication
  16. Screen documents for edits, failed redactions and prompt injection before agents read them

    Runs locally
    • 5 tools
    • Freemium
    • Security
  17. Scan AI images for marks, C2PA metadata and watermarks, then clean them with spend caps

    Runs locally
    • 5 tools
    • Freemium
    • Design and media
  18. Share agent skills across a team, scan them for risk and track which are used

    Runs locally
    • Freemium
    • Developer tools
  19. Check whether a product version is FIPS 140-3 validated, in NIST's queue or expiring

    Runs locally
    • 4 tools
    • Freemium
    • Security
  20. Caller ID, spam and fraud risk lookups for phone numbers, plus name and email search

    Not checked yet
    • 5 tools
    • Remote
    • Freemium
    • Communication
  21. Threat reports on files, URLs, domains and IPs for MCP clients, via VirusTotal's VTAI

    Not checked yet
    • Remote
    • Freemium
    • Security
  22. Check an x402 endpoint and its on-chain payer history before your agent pays it

    Runs locally
    • 3 tools
    • Freemium
    • Finance and payments
  23. Check an AI agent's INAM reputation before trusting it and sign receipts for finished work

    Not checked yet
    • 12 tools
    • Remote
    • Open source
    • Security
  24. Spending controls for agent payments: caps, allowed hosts and human approval for x402 APIs

    Runs locally
    • 11 tools
    • Freemium
    • Finance and payments
  25. Self-hosted AI memory on Postgres and pgvector, with hybrid search and a knowledge graph

    Runs locally
    • 4 tools
    • Open source
    • Knowledge and memory
  26. Approval inbox that lets an AI agent propose actions and wait for a human decision

    Not checked yet
    • 7 tools
    • Remote
    • Freemium
    • Developer tools
  27. MCP server that checks whether an x402 seller actually delivered before an agent pays

    Runs locally
    • Open source
    • Finance and payments
  28. Mandate gateway for AI trading agents: checks each order, seals reasoning, binds the fill

    Runs locally
    • 6 tools
    • Freemium
    • Finance and payments
  29. URL and IP safety check an agent calls before it fetches or opens a link

    Runs locally
    • 2 tools
    • Freemium
    • Security

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