Skip to content

MCP servers for security

43 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. Sign agent actions into a tamper-evident log and verify any agent's log from an MCP client

    • 10 tools
    • Remote
    • Open source
    • Security
  2. Ask why Korzen Bot Protection blocked a request and which AIs read your site

    • 4 tools
    • Remote
    • Free trial
    • Security
  3. A safer MCP for Dokploy: agents deploy and fix apps without seeing keys or secrets

    Not checked yet
    • 8 tools
    • Remote
    • Open source
    • Cloud and infrastructure
  4. Encrypted secrets for agents plus a phone approval step for sensitive actions

    Runs locally
    • Free trial
    • Security
  5. Check children's screen time and manage device rules from an AI assistant

    Not checked yet
    • Remote
    • Free trial
    • Security
  6. Local, reversible masking of client names and numbers before text goes to an AI

    Runs locally
    • Open source
    • Security
  7. Open-source control plane that firewalls MCP tool calls and caps agent model spend

    • Remote
    • Open source
    • Security
  8. Check an AI agent's action against signed rules before it commits, with auditable proof

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

    • Remote
    • Free trial
    • Security
  10. Flags fake engagement and prompt injection in AI-agent job board listings

    Runs locally
    • Open source
    • Security
  11. Moderate game and community chat from your agent, with a no-signup test key

    Not checked yet
    • 11 tools
    • Remote
    • Free trial
    • Security
  12. Static security scanner for MCP servers, agent skills and npm or PyPI packages

    Runs locally
    • Open source
    • Security
  13. YouTube video analysis, C2PA image marking and metadata removal, paid per call

    Not checked yet
    • 10 tools
    • Remote
    • Free trial
    • Design and media
  14. Public facts on a French phishing-awareness training service: plans, templates, security

    Not checked yet
    • 9 tools
    • Remote
    • Free trial
    • Security
  15. Test whether Cursor, Claude Code and VS Code can complete OAuth with your MCP server

    Not checked yet
    • Remote
    • Free trial
    • Developer tools
  16. Stamp tool results with their context and reject stale, duplicate or wrong-task outputs

    Not checked yet
    • Remote
    • Free trial
    • Security
  17. Manage managed Keycloak clusters, realms, SSO and users from an MCP client

    Not checked yet
    • 1 tool
    • Remote
    • Free trial
    • Security
  18. Offline security checks for code, dependencies and AI agent setup with six read-only tools

    Runs locally
    • Open source
    • Security
  19. Scan prompts, tool definitions and model output for injection, and guard tool calls

    Runs locally
    • Open source
    • AI models and LLM tooling
  20. Passive-by-default OSINT lookups for AI agents: DNS, WHOIS, IP, breaches, Shodan and more

    Runs locally
    • 16 tools
    • Open source
    • Security
  21. Look up hosts in a malware threat feed, read CVEs and scan URLs from your assistant

    Not checked yet
    • 5 tools
    • Remote
    • Free trial
    • Security
  22. Open-source evidence lake that grades security controls for audits

    Runs locally
    • Open source
    • Security
  23. Self-hosted gateway that lets AI agents use your accounts, with writes held for approval

    Not checked yet
    • Remote
    • Open source
    • Security
  24. Score a domain's SPF, DMARC, DKIM and other email protections from your AI client

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Communication
  25. Check an npm or PyPI package's Attestari grade before an agent installs it

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

    Not checked yet
    • Remote
    • Open source
    • Developer tools

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