Skip to content

MCP servers for security

576 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. Free read-only verification tools for agents, with a signed receipt on every call

    • 9 tools
    • Remote
    • Free
    • Security
  2. Gate every MCP tool call behind signed authorization and single-use capabilities

    Runs locally
    • Open source
    • Security
  3. Browser actions for AI agents that are classified, approved and logged

    Runs locally
    • 1 tool
    • Open source
    • Browser automation
  4. MCP wrapper that holds database writes until a second person approves them on their phone

    Runs locally
    • Open source
    • Databases
  5. Gives coding agents your API keys without letting the model ever read them

    Runs locally
    • 4 tools
    • Open source
    • Security
  6. Read-only Trino access for agents, run as the verified user so Trino policy decides

    Runs locally
    • 3 tools
    • Open source
    • Databases
  7. Rank security scanner findings by exposure, criticality and exploitability

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

    Runs locally
    • Open source
    • Security
  9. Free, keyless email checks for fake signups: disposable domains, typos, Gmail aliases

    • 4 tools
    • Remote
    • Free
    • Security
  10. Submit URLs for scanning and pivot through phishing evidence with 140+ read-only tools

    • 145 tools
    • Remote
    • Free
    • 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. Free pre-launch security checks for AI-built apps: leaked keys, Supabase RLS, env vars

    • 3 tools
    • Remote
    • Free
    • Security
  13. Keyless CVE, KEV, EPSS and advisory lookups with per-CVE internet exposure counts

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

    Runs locally
    • Open source
    • Security
  15. Real-time alerts for deepfake voices, impersonation and social engineering on live calls

    Not checked yet
    • Remote
    • Contact sales
    • Security
  16. Open-source MCP gateway that pins tools, holds risky calls and limits egress

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

    Runs locally
    • 4 tools
    • Open source
    • Developer tools
  18. Open-source control plane that firewalls MCP tool calls and caps agent model spend

    • Remote
    • Open source
    • Security
  19. Policy-gated agent spending with signed receipts and audit against the payment rail

    Runs locally
    • 5 tools
    • Open source
    • Finance and payments
  20. MSP-focused MCP server and CLI for WatchGuard Cloud across customers

    Runs locally
    • Open source
    • Security
  21. Read-only payment preflight for AI agents: pay, review or do-not-pay before signing

    • 9 tools
    • Remote
    • Open source
    • Security
  22. Checks JS/TS written by AI for risky patterns, fake npm packages and weakened tests

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  23. Agents use your API keys, SSH keys and wallets via a local broker and never hold them

    Runs locally
    • 10 tools
    • Free
    • Security
  24. Run an 88-test MCP spec compliance suite and get an A-F grade from CLI or agent

    Runs locally
    • 2 tools
    • Open source
    • Security
  25. Local input firewall that scans text, files and MCP metadata for prompt injection

    Runs locally
    • Open source
    • Security
  26. Lint CLAUDE.md, AGENTS.md and .mcp.json against your actual codebase

    Runs locally
    • Open source
    • Developer tools
  27. Electron IPC scaffolding, security audits, CSP and build-error diagnosis for assistants

    Runs locally
    • 8 tools
    • Open source
    • Developer tools
  28. npm registry intelligence, security audits and publish-side writes without the 2FA prompt

    Runs locally
    • 9 tools
    • Open source
    • Developer tools

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