Skip to content

MCP servers for security

27 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. Run agent-written code under a capability policy and see what it can touch first

    Runs locally
    • Freemium
    • Security
  2. Encrypted secrets for agents plus a phone approval step for sensitive actions

    Runs locally
    • Free trial
    • Security
  3. Security verdicts and a runtime guard for agent skills and MCP servers before they run

    Runs locally
    • Freemium
    • Security
  4. Local anonymiser that swaps client names and amounts for codes before Claude reads files

    Runs locally
    • Free trial
    • Security
  5. Query software inventory, vulnerabilities and end-of-life components

    • Remote
    • Free trial
    • Security
  6. Persistent, local-first memory for agents, stored as plain markdown

    Not checked yet
    • 11 tools
    • Remote
    • Freemium
    • Security
  7. Sealed microVM sandboxes for agents to run untrusted code, locally or in the cloud

    Not checked yet
    • Remote
    • Free trial
    • Developer tools
  8. Keeps API key values out of AI chats and deploys them to Cloudflare, Vercel or GitHub

    Runs locally
    • Freemium
    • Security
  9. Offline scan of local AI agent folders for heartbeat cost, exposed keys and planted memory

    Runs locally
    • 1 tool
    • Freemium
    • Security
  10. Repo triage, bug-fix pull requests and scanner reachability checks for coding agents

    Runs locally
    • 5 tools
    • Freemium
    • Developer tools
  11. See and manage a company's apps, access, devices and spend from an AI assistant

    Not checked yet
    • Remote
    • Freemium
    • Cloud and infrastructure
  12. 35 WHOIS, DNS, IP, reputation and threat-intelligence lookups for AI agents

    Not checked yet
    • 22 tools
    • Remote
    • Freemium
    • Security
  13. Local security layer for coding agents: secret redaction, injection checks and MCP proxy

    Runs locally
    • Freemium
    • Security
  14. Scan which credentials an AI coding agent running as you could read, offline

    Runs locally
    • 3 tools
    • Freemium
    • Security
  15. Scan MCP configs for leaked secrets and poisoned tools, and review AI-written code

    Not checked yet
    • 7 tools
    • Remote
    • Freemium
    • Security
  16. Per-account allow, ask or block rules for what AI apps may do in your connected services

    Not checked yet
    • 5 tools
    • Remote
    • Freemium
    • Security
  17. Free macOS debugging proxy that decrypts HTTPS and lets an assistant drive it over MCP

    Runs locally
    • Freemium
    • Developer tools
  18. Order a dedicated static outbound IPv4 over WireGuard, by API or through an agent

    Not checked yet
    • Remote
    • Free trial
    • Cloud and infrastructure
  19. Seven-tool proof loop that authorizes agent actions and records tamper-evident evidence

    Runs locally
    • 7 tools
    • Freemium
    • AI models and LLM tooling
  20. Detect and redact personal data in text, tuned to GDPR, UK GDPR, HIPAA and more

    Runs locally
    • 4 tools
    • Freemium
    • Security
  21. Sends files and secrets from agents to you without putting the link in the chat

    Runs locally
    • 6 tools
    • Freemium
    • Security
  22. Move VPN devices between countries and check protection by asking your assistant

    Runs locally
    • 14 tools
    • Freemium
    • Security
  23. Encrypted local secrets vault that lets AI agents use keys without seeing them

    Runs locally
    • 17 tools
    • Freemium
    • Security
  24. Security scanner that runs inside your AI editor for code written by AI builders

    Not checked yet
    • Remote
    • Freemium
    • Security

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