Skip to content

MCP servers for security

97 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. CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  3. Encrypted vault for .env files with scoped, audited MCP access for coding agents

    • 7 tools
    • Remote
    • Freemium
    • E-commerce
  4. A lockfile for MCP tools: blocks changed tool definitions and signs a receipt per call

    Runs locally
    • Open source
    • Security
  5. Encrypted secrets for agents plus a phone approval step for sensitive actions

    Runs locally
    • Free trial
    • Security
  6. Scan, read and write another process's memory from an AI assistant

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  7. Security verdicts and a runtime guard for agent skills and MCP servers before they run

    Runs locally
    • Freemium
    • Security
  8. Gives coding agents your API keys without letting the model ever read them

    Runs locally
    • 4 tools
    • Open source
    • Security
  9. Keep API keys in your OS keychain and give coding agents only what policy allows

    Runs locally
    • Open source
    • Security
  10. Local anonymiser that swaps client names and amounts for codes before Claude reads files

    Runs locally
    • Free trial
    • Security
  11. Strip GPS, EXIF, C2PA and AI prompts from photos, video, PDFs and RAW files locally

    Runs locally
    • 2 tools
    • Open source
    • Security
  12. Query software inventory, vulnerabilities and end-of-life components

    • Remote
    • Free trial
    • Security
  13. Local, reversible masking of client names and numbers before text goes to an AI

    Runs locally
    • Open source
    • Security
  14. Open-source MCP server scoring pull-request risk from blast radius and git history

    Runs locally
    • 4 tools
    • Open source
    • Developer tools
  15. MSP-focused MCP server and CLI for WatchGuard Cloud across customers

    Runs locally
    • Open source
    • Security
  16. Sealed microVM sandboxes for agents to run untrusted code, locally or in the cloud

    Not checked yet
    • Remote
    • Free trial
    • Developer tools
  17. Local application security scanner with an evidence ledger and honest gap reporting

    Runs locally
    • Open source
    • Security
  18. Pseudonymise or redact German court rulings and filings locally before AI sees them

    Runs locally
    • Paid
    • Legal and government
  19. Tamper-evident record of what an agent did, with free checking by anyone

    Runs locally
    • 4 tools
    • Freemium
    • Security
  20. Let agents run commands with your secrets without ever seeing the values

    Runs locally
    • 4 tools
    • Free
    • Security
  21. Keeps API key values out of AI chats and deploys them to Cloudflare, Vercel or GitHub

    Runs locally
    • Freemium
    • Security
  22. Prompt-injection scanner and tool-call gate for AI agents, run locally over stdio

    Runs locally
    • 3 tools
    • Open source
    • Security
  23. Offline trust certificates for code repositories that anyone can re-run and verify

    Runs locally
    • Open source
    • Security
  24. Local, deterministic repository context and merge-readiness checks for coding agents

    Runs locally
    • 4 tools
    • Open source
    • Developer tools
  25. Let an agent browse sites where you are already logged in, with encrypted local sessions

    Not checked yet
    • 3 tools
    • Remote
    • Free
    • Browser automation
  26. Offline scan of local AI agent folders for heartbeat cost, exposed keys and planted memory

    Runs locally
    • 1 tool
    • Freemium
    • Security
  27. Let AI agents run commands with your secrets while the values stay hidden and redacted

    Runs locally
    • 3 tools
    • Open source
    • Security
  28. Run an agent's code and shell commands in a locked-down Docker workspace

    Runs locally
    • 6 tools
    • Open source
    • Developer tools
  29. Hand coding tasks to sandboxed workers and verify each change before it is committed

    Runs locally
    • Open source
    • Developer tools

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