Skip to content

MCP servers for security

139 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 untrusted agent shell commands in a gVisor sandbox from any MCP client

    Runs locally
    • 1 tool
    • Open source
    • Security
  2. Self-hosted gateway that masks PII and signs receipts for AI access to your databases

    Runs locally
    • Open source
    • Security
  3. Record AI agent verdicts bound to file hashes and refuse stale ones before shipping

    Runs locally
    • Open source
    • Security
  4. Compare two logged-in identities to surface broken access control and IDOR

    Runs locally
    • Open source
    • Security
  5. Manage Pi-hole v6 DNS blocking, domains, clients, DHCP and query logs from an assistant

    Runs locally
    • 10 tools
    • Open source
    • Cloud and infrastructure
  6. Open-source MCP server for IP, DNS, mail-auth and MCP endpoint checks

    Runs locally
    • 13 tools
    • Open source
    • Security
  7. Collect API keys in a browser page and write them to .env without the model seeing them

    Runs locally
    • 1 tool
    • Open source
    • Security
  8. Wraps any MCP server so repeated write calls run once and every call is logged

    Runs locally
    • Open source
    • Developer tools
  9. Open-source order limits, phone approval and a kill switch for trading AI agents

    Runs locally
    • Open source
    • Finance and payments
  10. Authorization proxy that needs a rule check and AI judges to approve each tool call

    Runs locally
    • Open source
    • Security
  11. Look up known vulnerabilities in OSV.dev by package and version, and scan lockfiles

    Runs locally
    • 4 tools
    • Open source
    • Security
  12. Rules for each agent tool call, then a check of what a database really changed

    Runs locally
    • Open source
    • Security
  13. Self-hosted gateway that lets AI agents use your accounts, with writes held for approval

    Not checked yet
    • Remote
    • Open source
    • Security
  14. Check a website's post-quantum readiness and read internet-wide adoption figures

    Runs locally
    • 5 tools
    • Open source
    • Security
  15. Drafts a network allow list for an agent tool and test-runs it with the network blocked

    Runs locally
    • 3 tools
    • Open source
    • Security
  16. Let agents use and save 1Password secrets locally without ever seeing the plaintext

    Runs locally
    • Open source
    • Security
  17. Self-hosted control plane giving AI agents scoped, approved access to Docker and k8s

    Not checked yet
    • Remote
    • Open source
    • Developer tools
  18. Governed MCP gateway: approved tools only, each call policy-checked and recorded

    Runs locally
    • Open source
    • Security
  19. Lets agents order, validate, download and renew ACME TLS certificates over stdio

    Runs locally
    • Open source
    • Security
  20. Offline allow, ask or deny check for links and payments an AI agent is about to act on

    Runs locally
    • 2 tools
    • Open source
    • Security
  21. 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
  22. Self-hosted knowledge index where each search returns only what the caller may read

    Runs locally
    • Open source
    • Knowledge and memory
  23. Draft SOC 2 policies from your assistant, with 22 open-source templates

    Runs locally
    • 5 tools
    • Open source
    • Security
  24. Free passive security check for public websites, run from an MCP client like Claude Code

    Runs locally
    • 3 tools
    • Open source
    • Security
  25. Compare two Electron builds and see what changed in IPC, preload bridges and windows

    Runs locally
    • Open source
    • Security
  26. Install and run open-source OSINT tools in a local sandbox, asking before target runs

    Runs locally
    • 8 tools
    • Open source
    • Security
  27. Deterministic AST circuit breaker that blocks risky agent code before it runs

    Not checked yet
    • Remote
    • Open source
    • Security
  28. Write, test, lint and explain OPA Rego policies from any MCP client

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

    Runs locally
    • Open source
    • Cloud and infrastructure

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