Skip to content

MCP servers for security

66 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 checks that verify other MCP endpoints and signed price quotes

    Not checked yet
    • 3 tools
    • Remote
    • Free
    • Developer tools
  2. Dry-run Solana transactions before an agent signs: balance changes and token traps

    Not checked yet
    • 6 tools
    • Remote
    • Freemium
    • Finance and payments
  3. Scores and seals AI decisions into a Bitcoin-timestamped audit chain for compliance checks

    Not checked yet
    • Remote
    • Free trial
    • Finance and payments
  4. Self-hosted control plane giving AI agents scoped, approved access to Docker and k8s

    Not checked yet
    • Remote
    • Open source
    • Developer tools
  5. Query live risk, SBOMs, vulnerabilities and fixes from Safeguard's supply chain platform

    Not checked yet
    • Remote
    • Freemium
    • Security
  6. MCP server for database backups, health checks and audited changes by AI agents

    Not checked yet
    • 6 tools
    • Remote
    • Freemium
    • Databases
  7. Enterprise MCP gateway that authorizes each agent tool call per person, tool and argument

    Not checked yet
    • Remote
    • Contact sales
    • Security
  8. Manage and secure MCP servers on Speakeasy's AI control plane from an agent

    Not checked yet
    • Remote
    • Paid
    • Security
  9. Self-hosted OWASP ZAP operator that lets AI agents run guided security scans and reports

    Not checked yet
    • Remote
    • Open source
    • Security
  10. Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents

    Not checked yet
    • 2 tools
    • Remote
    • Open source
    • Security
  11. 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
  12. Open-source MCP proxy that enforces policies, budgets and approvals on agent tool calls

    Not checked yet
    • Remote
    • Open source
    • Security
  13. Read-only graph tools for cross-bank money-laundering cases, with Cypher for each claim

    Not checked yet
    • 12 tools
    • Remote
    • Open source
    • Finance and payments
  14. Local checks for sudo, systemd, sshd, ufw and secret leaks before an agent runs commands

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  15. Pay-per-call prompt-injection screening and sanitising API for AI agents, via x402

    Not checked yet
    • Remote
    • Paid
    • Security
  16. Simulate buys and sells to detect honeypots and rug-pull traps before trading a token

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Security
  17. Set up approval pipelines, escalation paths and teams in withHuman through an agent

    Not checked yet
    • Remote
    • Freemium
    • Security
  18. Masks Brazilian CPF, CNPJ and other personal data in text before it reaches an AI

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  19. Read-only library of 24 defensive security skills served over MCP

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  20. Send and verify one-time passcodes by SMS, WhatsApp and Telegram from an agent

    Not checked yet
    • 10 tools
    • Remote
    • Free trial
    • Communication
  21. Screens wallets and names against OFAC lists before an AI agent pays or trusts anyone

    Not checked yet
    • 10 tools
    • Remote
    • Freemium
    • Finance and payments
  22. Check an AI agent's INAM reputation before trusting it and sign receipts for finished work

    Not checked yet
    • 12 tools
    • Remote
    • Open source
    • Security
  23. Identity-aware AI tool gateway: every call runs as the requester, under rules, with audit

    Not checked yet
    • Remote
    • Contact sales
    • Security
  24. Permission-aware MCP server that lets Claude read your Odoo 18 or 19 data as one user

    Not checked yet
    • Remote
    • Paid
    • AI models and LLM tooling
  25. Approval inbox that lets an AI agent propose actions and wait for a human decision

    Not checked yet
    • 7 tools
    • Remote
    • Freemium
    • Developer tools
  26. Read-only WordPress plugin audits: vulnerabilities, leftovers, autoload weight and cron

    Not checked yet
    • Remote
    • Open source
    • Developer tools
  27. Plain-language checks of wallet approvals and signature requests, rated SAFE to RISK

    Not checked yet
    • Remote
    • Paid
    • Finance and payments

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