Skip to content

MCP servers for security

764 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. Score a website for AI-agent safety, llms.txt and machine-readable signals

    Runs locally
    • Free
    • AI models and LLM tooling
  2. Read-only access to Cyber Library, a free structured cybersecurity knowledge base

    Not checked yet
    • 6 tools
    • Remote
    • Free
    • Security
  3. Standards client that gives agents encrypted memory through your own SAIHM operator

    Runs locally
    • 8 tools
    • Open source
    • Knowledge and memory
  4. Check an agent's proposed action against its operator's mandate: permit, deny or escalate

    Not checked yet
    • Remote
    • Free
    • Security
  5. Look up malicious and vulnerable npm packages, free and without an API key

    Not checked yet
    • 7 tools
    • Remote
    • Free
    • Security
  6. Keyless access to verified AI voice-clone scam incidents, loss statistics and guidance

    Not checked yet
    • 5 tools
    • Remote
    • Free
    • Security
  7. 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
  8. Order smart-contract security audits and check agent payments before signing, paid in USDC

    Not checked yet
    • 6 tools
    • Remote
    • Paid
    • Security
  9. Decode ERC-20 approvals and token calls and compare them with the amount you expect

    Not checked yet
    • Remote
    • Free
    • Finance and payments
  10. Records a buyer's service request and checks what the service actually delivered

    Not checked yet
    • 3 tools
    • Remote
    • Free
    • Developer tools
  11. Checks A2A, MCP and OpenAPI declarations and logs dated changes to what suppliers publish

    Not checked yet
    • 13 tools
    • Remote
    • Free
    • Developer tools
  12. Self-check MCP server giving AI agents that spend money an indicative A-D risk grade

    Not checked yet
    • 3 tools
    • Remote
    • Free
    • Finance and payments
  13. Pay-for-results MCP gateway: quote, run and verify measurable agent tasks with refunds

    Not checked yet
    • 3 tools
    • Remote
    • Paid
    • Developer tools
  14. Typed yes/no and routing decisions from Jev: moderate, route models, guard tool calls

    Not checked yet
    • 7 tools
    • Remote
    • Paid
    • AI models and LLM tooling
  15. Local scanner that checks webhook handlers for missing or unsafe signature verification

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

    Runs locally
    • 4 tools
    • Open source
    • Knowledge and memory
  17. Free network, auth and web utilities for agents with no key and a zero-log policy

    Not checked yet
    • Remote
    • Free
    • Developer tools
  18. Permission-aware MCP server that lets Claude read your Odoo 18 or 19 data as one user

    Not checked yet
    • Remote
    • Paid
    • AI models and LLM tooling
  19. MCP server that checks whether an x402 seller actually delivered before an agent pays

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

    Runs locally
    • 9 tools
    • Open source
    • Communication
  21. Check what an npm package or file does at install time before your agent installs it

    Not checked yet
    • 2 tools
    • Remote
    • Free
    • Security
  22. Offline secret scanning MCP server that returns redacted findings to coding agents

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

    Runs locally
    • 6 tools
    • Open source
    • Security
  24. Run post-quantum, domain trust and security header scans from an AI agent

    Not checked yet
    • 3 tools
    • Remote
    • Free
    • Security
  25. Merged CVE, GHSA and OSV vulnerability feed with exploit flags, for security teams

    Not checked yet
    • 4 tools
    • Remote
    • Free
    • Security
  26. Read-only phishing domain intelligence over MCP for checking and investigating suspicious

    Not checked yet
    • 3 tools
    • Remote
    • Free
    • Security
  27. Read-only security scanner for code, infrastructure files and AI agent config

    Runs locally
    • Free
    • Security
  28. Search Microtoll Engine docs and scaffold an end-to-end-encrypted notes app locally

    Runs locally
    • 3 tools
    • Open source
    • Developer tools
  29. Encrypted local vault where your AI fetches API keys on demand and scans code for leaks

    Runs locally
    • 17 tools
    • Free
    • Security
  30. Anchor a file's SHA-256 hash on Base as proof of existence, and look up proofs

    Not checked yet
    • 2 tools
    • Remote
    • Paid
    • Files and documents

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