Skip to content

MCP servers for security

399 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 whether your exit IP works for ChatGPT, Claude and Gemini from your AI client

    Runs locally
    • 2 tools
    • Open source
    • AI models and LLM tooling
  2. Scan a deployed site for an exposed Supabase service_role key and audit its RLS

    Runs locally
    • 10 tools
    • Open source
    • Security
  3. Read-only MCP server that lets an agent read and verify its own tamper-evident action log

    Runs locally
    • Open source
    • Security
  4. Local ACT, BLOCK or ESCALATE check that runs before an AI agent takes an action

    Runs locally
    • 1 tool
    • Open source
    • Security
  5. Read-only guarded SQL access to eight database engines for AI agents

    Runs locally
    • 11 tools
    • Open source
    • Databases
  6. Read-only library of 24 defensive security skills served over MCP

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

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

    Runs locally
    • 5 tools
    • Freemium
    • Security
  9. Move files into an end-to-end encrypted vault, verified first, and tidy local folders

    Runs locally
    • 1 tool
    • Freemium
    • Files and documents
  10. Scan AI images for marks, C2PA metadata and watermarks, then clean them with spend caps

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

    Runs locally
    • Freemium
    • Developer tools
  12. Score a website for AI-agent safety, llms.txt and machine-readable signals

    Runs locally
    • Free
    • AI models and LLM tooling
  13. Caller ID, spam and fraud risk lookups for phone numbers, plus name and email search

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

    Not checked yet
    • Remote
    • Freemium
    • Security
  15. Standards client that gives agents encrypted memory through your own SAIHM operator

    Runs locally
    • 8 tools
    • Open source
    • Knowledge and memory
  16. Check an x402 endpoint and its on-chain payer history before your agent pays it

    Runs locally
    • 3 tools
    • Freemium
    • Finance and payments
  17. 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
  18. Send and read end-to-end encrypted documents from your own machine, by agent or CLI

    Runs locally
    • 3 tools
    • Freemium
    • Files and documents
  19. Post-quantum ML-DSA-65 signatures, provenance seals and decision receipts paid via x402

    Runs locally
    • 5 tools
    • Freemium
    • Security
  20. Issue and verify post-quantum agent passports and signed decision receipts offline

    Runs locally
    • 7 tools
    • Freemium
    • Security
  21. Spending controls for agent payments: caps, allowed hosts and human approval for x402 APIs

    Runs locally
    • 11 tools
    • Freemium
    • Finance and payments
  22. Local scanner that checks webhook handlers for missing or unsafe signature verification

    Runs locally
    • 2 tools
    • Open source
    • Security
  23. Self-hosted AI memory on Postgres and pgvector, with hybrid search and a knowledge graph

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

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

    Runs locally
    • Open source
    • Finance and payments
  26. Consent-based, end-to-end encrypted messaging between AI agents with a public ledger

    Runs locally
    • 9 tools
    • Open source
    • Communication
  27. Offline secret scanning MCP server that returns redacted findings to coding agents

    Runs locally
    • 2 tools
    • Open source
    • Security
  28. macOS Keychain secret broker where an agent can use your API keys but never read them

    Runs locally
    • 6 tools
    • Open source
    • Security
  29. Mandate gateway for AI trading agents: checks each order, seals reasoning, binds the fill

    Runs locally
    • 6 tools
    • Freemium
    • Finance and payments

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