Skip to content

MCP servers for security

203 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. Authorization proxy that needs a rule check and AI judges to approve each tool call

    Runs locally
    • Open source
    • Security
  2. Lint Dockerfiles for root users, latest tags, secrets in ENV or ARG and more

    Runs locally
    • 3 tools
    • Open source
    • Developer tools
  3. Decode JWTs without trusting them, flag risky claims, verify signatures, mint test tokens

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

    Runs locally
    • 4 tools
    • Open source
    • Security
  5. Grades a site's security headers and explains each one, over stdio

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

    Runs locally
    • Open source
    • Security
  7. Score a domain's SPF, DMARC, DKIM and other email protections from your AI client

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Communication
  8. Check a website's post-quantum readiness and read internet-wide adoption figures

    Runs locally
    • 5 tools
    • Open source
    • Security
  9. Adopt, read, verify and record an Open Entity identity for an AI agent, no auth

    Not checked yet
    • 6 tools
    • Remote
    • Open source
    • Security
  10. Drafts a network allow list for an agent tool and test-runs it with the network blocked

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

    Runs locally
    • Open source
    • Security
  12. Local MCP server that redacts personal data and secrets in text before it reaches a model

    Runs locally
    • 1 tool
    • Open source
    • Security
  13. Governed MCP gateway: approved tools only, each call policy-checked and recorded

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

    Runs locally
    • Open source
    • Security
  15. 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
  16. 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
  17. Self-hosted knowledge index where each search returns only what the caller may read

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

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

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

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

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

    Runs locally
    • 10 tools
    • Open source
    • Developer tools
  23. Countersigned proof-of-delivery receipts for work sold between AI agents

    Not checked yet
    • 4 tools
    • Remote
    • Open source
    • Security
  24. Static safety scan of MCP configs that returns SAFE, REVIEW, BLOCK or UNKNOWN verdicts

    Runs locally
    • Open source
    • Security
  25. Inspect and manage a UniFi network: devices, clients, WiFi, firewall and VPN

    Runs locally
    • Open source
    • Cloud and infrastructure
  26. Secret broker that injects credentials at the point of use, never into the model

    Runs locally
    • Open source
    • Security
  27. Open forum and end-to-end encrypted direct messages for AI agents, keys held client-side

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

    Runs locally
    • Open source
    • Security
  29. Local static audit of AI model files with hash-bound evidence for deployment reviews

    Not checked yet
    • Remote
    • Open source
    • AI models and LLM tooling

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