Skip to content

MCP servers for security

824 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. Let your AI assistant send encrypted files and secrets, and collect files

    Not checked yet
    • Remote
    • Freemium
    • Files and documents
  2. Verify AI agent identity, trust scores and mandate conformance on a hosted 61-tool server

    Not checked yet
    • 12 tools
    • Remote
    • Freemium
    • Security
  3. BNB Chain token risk ratings, honeypot checks and rug pull forensics for agents

    Not checked yet
    • 4 tools
    • Remote
    • Freemium
    • Finance and payments
  4. Collect API keys in a browser page and write them to .env without the model seeing them

    Runs locally
    • 1 tool
    • Open source
    • Security
  5. Wraps any MCP server so repeated write calls run once and every call is logged

    Runs locally
    • Open source
    • Developer tools
  6. Security checks for coding agents: dependency audits and evidence for fixes

    Not checked yet
    • Remote
    • Freemium
    • Security
  7. Checks EVM wallets for EIP-7702 delegations that could be a sweeper contract

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Security
  8. Checks a crypto recipient for address-poisoning lookalikes and bad checksums

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Security
  9. Flags phishing lookalikes of wallet, exchange and dapp links before you connect

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Finance and payments
  10. Scans GitHub repos and shell commands for malware tricks before an agent runs them

    Not checked yet
    • 4 tools
    • Remote
    • Freemium
    • Developer tools
  11. Secrets manager MCP server that runs commands with API keys the model never sees

    Runs locally
    • 2 tools
    • Open source
    • Security
  12. Check what trackers load before consent and get a Consent Mode v2 cookie banner

    Not checked yet
    • Remote
    • Freemium
    • Legal and government
  13. Hosted MCP check that reviews an agent's planned purchase, booking or message first

    Not checked yet
    • 4 tools
    • Remote
    • Freemium
    • Security
  14. Check a Vercel and Supabase repo for missing RLS, leaked keys and webhook gaps

    Runs locally
    • Freemium
    • Security
  15. Scan a site for trackers firing before cookie consent, with evidence and fixes

    Not checked yet
    • 16 tools
    • Remote
    • Freemium
    • Security
  16. Structural code-quality scoring for coding agents, from SLOP to PLATINUM, run locally

    Runs locally
    • Open source
    • Developer tools
  17. Open-source order limits, phone approval and a kill switch for trading AI agents

    Runs locally
    • Open source
    • Finance and payments
  18. Give a coding agent the dependency graph: scan, explain and diff packages

    Runs locally
    • 3 tools
    • Open source
    • Security
  19. Free macOS debugging proxy that decrypts HTTPS and lets an assistant drive it over MCP

    Runs locally
    • Freemium
    • Developer tools
  20. Scans an MCP server for open access and overreaching tools before an agent connects

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Security
  21. Registry, runtime gate and audit trail for the agent skills your organisation approves

    Not checked yet
    • 3 tools
    • Remote
    • Freemium
    • Security
  22. Bind, rotate and audit SQL Server and SSRS TLS certificates from an AI assistant

    Runs locally
    • 20 tools
    • Freemium
    • Databases
  23. OSINT lookups and scam investigations whose every answer links back to its evidence

    Not checked yet
    • Remote
    • Freemium
    • Security
  24. Screen untrusted text for prompt injection and jailbreaks before it reaches your LLM

    Not checked yet
    • Remote
    • Freemium
    • AI models and LLM tooling
  25. MCP server that routes an agent's npm, pip and docker installs through a package firewall

    Not checked yet
    • 10 tools
    • Remote
    • Freemium
    • Security
  26. MCP server giving AI assistants honeypot threat intelligence on scanners and CVE probing

    Not checked yet
    • 14 tools
    • Remote
    • Freemium
    • Security
  27. Seven-tool proof loop that authorizes agent actions and records tamper-evident evidence

    Runs locally
    • 7 tools
    • Freemium
    • AI models and LLM tooling

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