Skip to content

MCP servers for security

495 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. Pay-per-check reviewer for agent drafts, handed-off work and skills before install

    Not checked yet
    • 5 tools
    • Remote
    • Paid
    • Security
  2. Install and run open-source OSINT tools in a local sandbox, asking before target runs

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

    Not checked yet
    • Remote
    • Open source
    • Security
  4. Check AI-generated code for security issues and declared-vs-actual drift before merging

    Not checked yet
    • Remote
    • Freemium
    • Developer tools
  5. Signed checks of x402 sellers on Base and remote MCP servers before your agent pays

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

    Runs locally
    • 10 tools
    • Open source
    • Developer tools
  7. Look up changes in MCP server, skill and plugin descriptions before an agent uses them

    Runs locally
    • 4 tools
    • Freemium
    • Security
  8. Countersigned proof-of-delivery receipts for work sold between AI agents

    Not checked yet
    • 4 tools
    • Remote
    • Open source
    • Security
  9. Pre-payment risk checks for AI agents: screen a counterparty before x402 payments

    Runs locally
    • 4 tools
    • Paid
    • Security
  10. Rule-based review of diffs for leaked secrets and unsafe database migrations

    Not checked yet
    • Remote
    • Freemium
    • Developer tools
  11. Search a safety-scanned directory of agent skills and check any skill before installing

    Not checked yet
    • 6 tools
    • Remote
    • Freemium
    • Developer tools
  12. Static safety scan of MCP configs that returns SAFE, REVIEW, BLOCK or UNKNOWN verdicts

    Runs locally
    • Open source
    • Security
  13. Scan AI-built apps for open databases, exposed keys and unsafe functions with proof

    Runs locally
    • Freemium
    • Security
  14. Inspect and manage a UniFi network: devices, clients, WiFi, firewall and VPN

    Runs locally
    • Open source
    • Cloud and infrastructure
  15. Read-only witness for local git projects and sites, naming what would be lost

    Runs locally
    • Free
    • Developer tools
  16. Read-only honeypot and tax simulation for Solana and Base tokens, paid per call in USDC

    Runs locally
    • Freemium
    • Security
  17. Read-only search of an OSINT tool and guide registry, with consent classes for each tool

    Not checked yet
    • 6 tools
    • Remote
    • Free
    • Security
  18. Build and manage GDPR-compliant, EU-hosted forms by describing them to an assistant

    Not checked yet
    • 5 tools
    • Remote
    • Freemium
    • Productivity
  19. Secret broker that injects credentials at the point of use, never into the model

    Runs locally
    • Open source
    • Security
  20. Let a coding agent use temporary credentials without the values entering the chat

    Runs locally
    • Free
    • Security
  21. Encrypted local secrets vault that lets AI agents use keys without seeing them

    Runs locally
    • 17 tools
    • Freemium
    • Security
  22. Scan a GitHub repository for vulnerabilities from a coding agent, with proof per finding

    Not checked yet
    • Remote
    • Freemium
    • Developer tools
  23. Check what a repository would run on your machine before you clone or open it

    Runs locally
    • 2 tools
    • Freemium
    • Security
  24. Check x402 payment requests and Québec contractors before your agent pays

    Not checked yet
    • 6 tools
    • Remote
    • Freemium
    • Finance and payments
  25. Local vault MCP server that lets agents use API keys without ever seeing them

    Runs locally
    • 1 tool
    • Paid
    • Security
  26. Open forum and end-to-end encrypted direct messages for AI agents, keys held client-side

    Runs locally
    • Open source
    • Communication
  27. Remote MCP set of 15 smart-contract, Solana and HTTP 402 security checks for DeFi agents

    Not checked yet
    • 3 tools
    • Remote
    • Freemium
    • Finance and payments

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