Skip to content

MCP servers for security

88 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 MCP server that shows which git name, email and SSH key a repo will use

    Runs locally
    • 6 tools
    • Open source
    • Developer tools
  2. Find end-of-life runtimes, packages and Actions in a repo, with file, line and source

    Runs locally
    • Open source
    • Developer tools
  3. Approval gateway that keeps AI assistants from reading or changing your data unchecked

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

    Runs locally
    • 2 tools
    • Open source
    • Security
  5. Passive-by-default OSINT lookups for AI agents: DNS, WHOIS, IP, breaches, Shodan and more

    Runs locally
    • 16 tools
    • Open source
    • Security
  6. Local security scanner that checks AI-written code and drives a scan, fix, rescan loop

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

    Runs locally
    • 18 tools
    • Open source
    • Communication
  8. Signed, sealed handoffs between AI agents, with trust decided by the receiver

    Runs locally
    • Open source
    • Security
  9. MCP server and CLI giving coding agents version-matched docs and a dependency check

    Runs locally
    • 2 tools
    • Open source
    • Developer tools
  10. Read-only preflight checks for MCP and x402 endpoints before an agent depends on them

    Runs locally
    • 2 tools
    • Open source
    • Developer tools
  11. Email MCP server for Gmail, Outlook and IMAP that fences messages against prompt injection

    Runs locally
    • 12 tools
    • Open source
    • Communication
  12. Passive scan of a website's AI-agent readiness: robots, llms.txt, JSON-LD, MCP, security

    Runs locally
    • Open source
    • Marketing and SEO
  13. Manage Pi-hole v6 DNS blocking, domains, clients, DHCP and query logs from an assistant

    Runs locally
    • 10 tools
    • Open source
    • Cloud and infrastructure
  14. Docker-run MCP server for finding public emails and subdomains of a domain

    Runs locally
    • 4 tools
    • Open source
    • Security
  15. Docker-run MCP server that identifies the CMS, server and frameworks behind a website

    Runs locally
    • 3 tools
    • Open source
    • Security
  16. Offline security scans for AI-written code: seven open-source scanners, one report

    Runs locally
    • Open source
    • Security
  17. Pins MCP tool definitions at approval and blocks the session when they change

    Runs locally
    • Open source
    • Security
  18. Collect API keys in a browser page and write them to .env without the model seeing them

    Runs locally
    • 1 tool
    • Open source
    • Security
  19. Secrets manager MCP server that runs commands with API keys the model never sees

    Runs locally
    • 2 tools
    • Open source
    • Security
  20. Structural code-quality scoring for coding agents, from SLOP to PLATINUM, run locally

    Runs locally
    • Open source
    • Developer tools
  21. Give a coding agent the dependency graph: scan, explain and diff packages

    Runs locally
    • 3 tools
    • Open source
    • Security
  22. Remote MCP server giving defender agents ledger reads and findings on a coding-agent fleet

    Not checked yet
    • Remote
    • Free
    • Security
  23. Lint Dockerfiles for root users, latest tags, secrets in ENV or ARG and more

    Runs locally
    • 3 tools
    • Open source
    • Developer tools
  24. Decode JWTs without trusting them, flag risky claims, verify signatures, mint test tokens

    Runs locally
    • 3 tools
    • Open source
    • Security
  25. Rules for each agent tool call, then a check of what a database really changed

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

    Not checked yet
    • Remote
    • Open source
    • Security
  27. Let agents use and save 1Password secrets locally without ever seeing the plaintext

    Runs locally
    • Open source
    • Security
  28. Threat-intelligence verdicts on a URL, domain or IP before a coding agent connects

    Not checked yet
    • Remote
    • Free
    • Security

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