Skip to content

MCP servers for security

86 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. Self-hosted control plane giving AI agents scoped, approved access to Docker and k8s

    Not checked yet
    • Remote
    • Open source
    • Developer tools
  2. Score AI agent runs for quality, PII leaks, prompt injection and cost, on your own machine

    Runs locally
    • 3 tools
    • Open source
    • AI models and LLM tooling
  3. Install and run open-source OSINT tools in a local sandbox, asking before target runs

    Runs locally
    • 8 tools
    • Open source
    • Security
  4. Write, test, lint and explain OPA Rego policies from any MCP client

    Runs locally
    • 10 tools
    • Open source
    • Developer tools
  5. Inspect and manage a UniFi network: devices, clients, WiFi, firewall and VPN

    Runs locally
    • Open source
    • Cloud and infrastructure
  6. Journal, approve or block, and sandbox every MCP tool call your AI agent makes

    Runs locally
    • Open source
    • Security
  7. Typed, policy-checked server operations for AI agents, with approvals and an audit log

    Runs locally
    • 11 tools
    • Open source
    • Developer tools
  8. Local checks for sudo, systemd, sshd, ufw and secret leaks before an agent runs commands

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  9. Self-hosted customer feedback search, stats and themes, with PII redacted at ingest

    Runs locally
    • Open source
    • Analytics and data
  10. Pins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets

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

    Runs locally
    • Open source
    • Files and documents
  12. 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
  13. Identity-aware AI tool gateway: every call runs as the requester, under rules, with audit

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

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

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

    Runs locally
    • 13 tools
    • Open source
    • Security
  17. 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
  18. Let an agent clear node_modules and other junk folders, only inside roots you allow

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  19. On-premises document retrieval for agents, with folder-level access rules checked first

    Runs locally
    • Open source
    • Knowledge and memory
  20. Read-only npm preflight: reviews what install scripts do before packages run

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

    Runs locally
    • 9 tools
    • Open source
    • Knowledge and memory
  22. Guard agents' PostgreSQL and MySQL access with SQL audit, masking and write approval

    Not checked yet
    • Remote
    • Open source
    • Databases
  23. Find and strip zero-width, bidi and tag characters hidden in text, offline

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

    Runs locally
    • Open source
    • Security
  25. 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.