Skip to content

MCP servers for security

118 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. Let a coding agent use temporary credentials without the values entering the chat

    Runs locally
    • Free
    • Security
  2. Encrypted local secrets vault that lets AI agents use keys without seeing them

    Runs locally
    • 17 tools
    • Freemium
    • Security
  3. Local vault MCP server that lets agents use API keys without ever seeing them

    Runs locally
    • 1 tool
    • Paid
    • Security
  4. Journal, approve or block, and sandbox every MCP tool call your AI agent makes

    Runs locally
    • Open source
    • Security
  5. Security scanner that runs inside your AI editor for code written by AI builders

    Not checked yet
    • Remote
    • Freemium
    • Security
  6. Manage Ghost Networks private mesh networks, hubs, VPN and devices from your AI client

    Runs locally
    • Paid
    • Cloud and infrastructure
  7. Local checks for sudo, systemd, sshd, ufw and secret leaks before an agent runs commands

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  8. Let two companies' AI agents work together on a signed record, with people approving

    Not checked yet
    • Remote
    • Free
    • Communication
  9. Self-hosted customer feedback search, stats and themes, with PII redacted at ingest

    Runs locally
    • Open source
    • Analytics and data
  10. Read your Golem agent fleet sessions, live activity and signed record from any client

    Not checked yet
    • Remote
    • Free
    • Security
  11. Pins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets

    Runs locally
    • 2 tools
    • Open source
    • Security
  12. Read-only MCP server that lints and budgets CLAUDE.md, AGENTS.md and other steering files

    Runs locally
    • Open source
    • Files and documents
  13. 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
  14. Identity-aware AI tool gateway: every call runs as the requester, under rules, with audit

    Not checked yet
    • Remote
    • Contact sales
    • Security
  15. Consent-based, end-to-end encrypted messaging between AI agents with a public ledger

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

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

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

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

    Runs locally
    • 13 tools
    • Open source
    • Security
  22. Let an agent clear node_modules and other junk folders, only inside roots you allow

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  23. Read-only npm preflight: reviews what install scripts do before packages run

    Runs locally
    • Open source
    • Security
  24. Tamper-evident local record of what your AI agent did, plus verifiable markdown memory

    Runs locally
    • 9 tools
    • Open source
    • Knowledge and memory
  25. Find and strip zero-width, bidi and tag characters hidden in text, offline

    Runs locally
    • 5 tools
    • Open source
    • Security
  26. Access control for AI agents: allow, hold for approval or block each tool call

    Runs locally
    • Open source
    • Security
  27. MCP server and open protocol for signed messages between agents with human-gated approvals

    Runs locally
    • Open source
    • Developer tools

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