Skip to content

MCP servers for security

254 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. Open forum and end-to-end encrypted direct messages for AI agents, keys held client-side

    Runs locally
    • Open source
    • Communication
  2. Journal, approve or block, and sandbox every MCP tool call your AI agent makes

    Runs locally
    • Open source
    • Security
  3. 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
  4. Manage SimpleLogin aliases, mailboxes, domains and settings from an MCP client

    Runs locally
    • 14 tools
    • Open source
    • Security
  5. Open-source MCP proxy that enforces policies, budgets and approvals on agent tool calls

    Not checked yet
    • Remote
    • Open source
    • Security
  6. Verify blockchain timestamp proofs offline and anchor file hashes through ProofLedger

    Runs locally
    • Open source
    • Security
  7. Policy-check every x402 paywall an AI agent meets before any payment moves

    Runs locally
    • Open source
    • Finance and payments
  8. Typed, policy-checked server operations for AI agents, with approvals and an audit log

    Runs locally
    • 11 tools
    • Open source
    • Developer tools
  9. MCP server to validate Guard Core SecurityConfig, search its docs and check threats

    Runs locally
    • Open source
    • Security
  10. Pre-install safety checks for AI agents: known traps, tested fixes and malware reports

    Not checked yet
    • 10 tools
    • Remote
    • Free
    • Security
  11. Check an AI microservice's trust score before calling it, and rate it afterwards

    Runs locally
    • Free
    • Security
  12. Local checks for sudo, systemd, sshd, ufw and secret leaks before an agent runs commands

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  13. Let two companies' AI agents work together on a signed record, with people approving

    Not checked yet
    • Remote
    • Free
    • Communication
  14. CNCF release notes turned into typed changes, with a local stack version check

    Runs locally
    • 1 tool
    • Open source
    • Cloud and infrastructure
  15. Self-hosted customer feedback search, stats and themes, with PII redacted at ingest

    Runs locally
    • Open source
    • Analytics and data
  16. Read your Golem agent fleet sessions, live activity and signed record from any client

    Not checked yet
    • Remote
    • Free
    • Security
  17. Local MCP runtime that checks, approves and records every agent tool call

    Runs locally
    • Open source
    • Developer tools
  18. Verify, explain and audit regexes for ReDoS and engine compatibility, offline

    Runs locally
    • 5 tools
    • Open source
    • Developer tools
  19. Pins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets

    Runs locally
    • 2 tools
    • Open source
    • Security
  20. Read-only MCP server that lints and budgets CLAUDE.md, AGENTS.md and other steering files

    Runs locally
    • Open source
    • Files and documents
  21. Plain-English security checks for AI-built apps, with fix requests for your coding agent

    Runs locally
    • Open source
    • Security
  22. Approve agent actions from your phone; sandboxed browser vault with saved logins

    Runs locally
    • Free
    • Security
  23. Masks Brazilian CPF, CNPJ and other personal data in text before it reaches an AI

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • Security
  24. Local MCP tools that redact secrets in files, scan commits and verify webhooks for agents

    Runs locally
    • 4 tools
    • Open source
    • Security
  25. Check whether your exit IP works for ChatGPT, Claude and Gemini from your AI client

    Runs locally
    • 2 tools
    • Open source
    • AI models and LLM tooling
  26. Scan a deployed site for an exposed Supabase service_role key and audit its RLS

    Runs locally
    • 10 tools
    • Open source
    • Security

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