Skip to content

MCP servers for security

603 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. Gives coding agents your API keys without letting the model ever read them

    Runs locally
    • 4 tools
    • Open source
    • Security
  2. Check children's screen time and manage device rules from an AI assistant

    Not checked yet
    • Remote
    • Free trial
    • Security
  3. Read-only Trino access for agents, run as the verified user so Trino policy decides

    Runs locally
    • 3 tools
    • Open source
    • Databases
  4. Check a store or product page for scam and dark-pattern signals before buying

    Runs locally
    • 2 tools
    • Paid
    • E-commerce
  5. Rank security scanner findings by exposure, criticality and exploitability

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

    Runs locally
    • Open source
    • Security
  7. Pay-per-check on-chain risk verdicts for EVM tokens and wallets, built for agents

    • 3 tools
    • Remote
    • Paid
    • Security
  8. Local anonymiser that swaps client names and amounts for codes before Claude reads files

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

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

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

    Runs locally
    • Open source
    • Security
  12. Open-source MCP gateway that pins tools, holds risky calls and limits egress

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

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

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

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

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

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

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  19. Check an AI agent's action against signed rules before it commits, with auditable proof

    • 7 tools
    • Remote
    • Free trial
    • Security
  20. Give each AI agent its own inbox, saved logins and 2FA codes

    • Remote
    • Free trial
    • Security
  21. Pay-per-call USDT payment checks and address risk scores for agents

    • 4 tools
    • Remote
    • Paid
    • Finance and payments
  22. 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
  23. Local input firewall that scans text, files and MCP metadata for prompt injection

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

    Not checked yet
    • Remote
    • Free trial
    • Developer tools
  25. Lint CLAUDE.md, AGENTS.md and .mcp.json against your actual codebase

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

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

    Runs locally
    • 9 tools
    • Open source
    • Developer tools
  28. Screen an x402 payment counterparty with allow, review or block before an agent pays

    Runs locally
    • 1 tool
    • Open source
    • Security

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