Skip to content

MCP servers for security

254 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 MCP server that lets an agent read and verify its own tamper-evident action log

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

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

    Runs locally
    • 11 tools
    • Open source
    • Databases
  4. Check whether an AI agent holds TAP certifications, read live from the chain

    Not checked yet
    • 4 tools
    • Remote
    • Free
    • Security
  5. Read-only library of 24 defensive security skills served over MCP

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  6. Score a website for AI-agent safety, llms.txt and machine-readable signals

    Runs locally
    • Free
    • AI models and LLM tooling
  7. Standards client that gives agents encrypted memory through your own SAIHM operator

    Runs locally
    • 8 tools
    • Open source
    • Knowledge and memory
  8. Look up malicious and vulnerable npm packages, free and without an API key

    Not checked yet
    • 7 tools
    • Remote
    • Free
    • Security
  9. 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
  10. Local scanner that checks webhook handlers for missing or unsafe signature verification

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

    Runs locally
    • 4 tools
    • Open source
    • Knowledge and memory
  12. MCP server that checks whether an x402 seller actually delivered before an agent pays

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

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

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

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

    Runs locally
    • 6 tools
    • Open source
    • Security
  17. Read-only security scanner for code, infrastructure files and AI agent config

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

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

    Runs locally
    • 17 tools
    • Free
    • Security
  20. Local approvals and audit so coding agents use credentials without ever seeing them

    Runs locally
    • Free
    • Security
  21. Check whether an IP or your own network exit suits ChatGPT, Claude and Gemini

    Not checked yet
    • 4 tools
    • Remote
    • Free
    • AI models and LLM tooling
  22. Exact-action approval and signed receipts for consequential AI agent actions

    Runs locally
    • Open source
    • Security
  23. Network scanner for AI agents: host discovery, port scans, DNS, ARP and mDNS lookups

    Runs locally
    • 13 tools
    • Open source
    • Security
  24. Hosted MCP checks that npm and PyPI packages, versions and functions actually exist

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  25. Go daemon giving AI agents scoped Linux host tools over MCP instead of an SSH shell

    Not checked yet
    • 7 tools
    • Remote
    • Open source
    • Cloud and infrastructure
  26. Find vendor trust centers, analyze SOC 2 reports and request access from an AI client

    Not checked yet
    • 15 tools
    • Remote
    • Open source
    • Security
  27. Let an agent clear node_modules and other junk folders, only inside roots you allow

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  28. Read-only Postgres access for agents that parses SQL and refuses write-capable roles

    Runs locally
    • Open source
    • Databases

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