Skip to content

MCP servers for security

203 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. Read-only network config checks: drift, CIS/PCI, 802.1X, certs and change risk

    Runs locally
    • 12 tools
    • Open source
    • Knowledge and memory
  2. CVSS scoring, IOC extraction, email header triage and KEV lookup for analysts

    Runs locally
    • 10 tools
    • Open source
    • Knowledge and memory
  3. Find which CI security checks are missing or cannot fail the build in a repository

    Runs locally
    • Open source
    • Security
  4. 35 WHOIS, DNS, IP, reputation and threat-intelligence lookups for AI agents

    Not checked yet
    • 22 tools
    • Remote
    • Freemium
    • Security
  5. Approval gateway that keeps AI assistants from reading or changing your data unchecked

    Runs locally
    • Open source
    • Security
  6. Free MCP server that checks lockfiles, Node.js and PHP versions and Dockerfiles for flaws

    Not checked yet
    • Remote
    • Open source
    • Security
  7. Self-hosted fleet of persistent, logged-in stealth Chrome sessions for AI agents

    Runs locally
    • Open source
    • Browser automation
  8. Mac key vault where agents get scoped, expiring tokens and never the API keys

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

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

    Runs locally
    • 16 tools
    • Open source
    • Security
  11. Review and block risky AI agent actions, installs and MCP calls on your machine

    Runs locally
    • Freemium
    • Security
  12. Persistent sandbox for coding agents: run commands, edit files, manage Git and sessions

    Not checked yet
    • 1 tool
    • Remote
    • Open source
    • Developer tools
  13. Open-source MCP gate that signs an allow, deny or hold before each agent tool call

    Not checked yet
    • Remote
    • Open source
    • Security
  14. Read-only CVE triage that explains each verdict from KEV, EPSS and exploit data

    Runs locally
    • 1 tool
    • Open source
    • Security
  15. Telegram MCP server with a separate key per AI client, scoped to chosen chats

    Runs locally
    • 18 tools
    • Open source
    • Communication
  16. Read-only operator view of Vongola, a Rust TLS reverse proxy built on Pingora

    Runs locally
    • Open source
    • Cloud and infrastructure
  17. Rust reverse-engineering MCP server that returns evidence-backed findings on binaries

    Runs locally
    • Open source
    • Security
  18. File ownership, expiring shares and audit trail for SaaS apps, exposed to agents over MCP

    Runs locally
    • Open source
    • Files and documents
  19. Read-only preflight checks for MCP and x402 endpoints before an agent depends on them

    Runs locally
    • 2 tools
    • Open source
    • Developer tools
  20. Apache-2.0 SDK for hash-chained agent audit logs, policy checks and human approvals

    Runs locally
    • Freemium
    • Security
  21. Signed proof that a drone, robot or vehicle was at a place, for audit and logistics

    Runs locally
    • Freemium
    • Security
  22. Open-source gateway that routes AI requests by privacy policy and governs tool access

    Not checked yet
    • Remote
    • Open source
    • Knowledge and memory
  23. Give an AI assistant its own Bitwarden vault for logins, 2FA codes and passkeys

    Runs locally
    • 7 tools
    • Open source
    • Security
  24. Python library that adds permission tiers, approval gates and audit logs to MCP servers

    Runs locally
    • Open source
    • Security
  25. Open-source evidence lake that grades security controls for audits

    Runs locally
    • Open source
    • Security
  26. Run untrusted agent shell commands in a gVisor sandbox from any MCP client

    Runs locally
    • 1 tool
    • Open source
    • Security
  27. Local file inspector and guarded editor that flags hidden content and text aimed at AI

    Runs locally
    • Freemium
    • Files and documents

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