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. Let an AI agent pay USDC on NEAR only within owner-signed mandates, with a signed ledger

    Runs locally
    • 4 tools
    • Open source
    • Finance and payments
  2. Local permission gate that allows or stops an agent's tool call before it runs

    Runs locally
    • Open source
    • Security
  3. Administer a FoxAuth OAuth 2.1 and OpenID Connect server from an AI agent

    Not checked yet
    • 8 tools
    • Remote
    • Free
    • Developer tools
  4. Kubernetes MCP server where every change needs a passkey approval from your phone

    Runs locally
    • Open source
    • Cloud and infrastructure
  5. Hash and sign evidence of what AI agents did, mapped to AI governance frameworks

    Runs locally
    • Open source
    • Security
  6. Tool router and prompt firewall that keeps only a few MCP tools active per turn

    Not checked yet
    • Remote
    • Freemium
    • Security
  7. Run compliance readiness scans on your code from Claude Code, Cursor or Codex

    Runs locally
    • 4 tools
    • Open source
    • Security
  8. A local gateway that holds agent calls to MCP tools that changed after you approved them

    Runs locally
    • Freemium
    • Security
  9. Proxmox VE access across many clusters, with deletes held behind plan, approve and apply

    Runs locally
    • 2 tools
    • Open source
    • Cloud and infrastructure
  10. Prompt-injection scanner and tool-call gate for AI agents, run locally over stdio

    Runs locally
    • 3 tools
    • Open source
    • Security
  11. Registry that records who authorised an AI agent, within what limits and until when

    Runs locally
    • 12 tools
    • Open source
    • Security
  12. Offline trust certificates for code repositories that anyone can re-run and verify

    Runs locally
    • Open source
    • Security
  13. Rust MCP server for the Juniper Mist cloud with scoped tokens and two-person changes

    Runs locally
    • 3 tools
    • Open source
    • Cloud and infrastructure
  14. Read-only MCP tools that list and flag outstanding ERC-20, Permit2 and EIP-3009 approvals

    Runs locally
    • 2 tools
    • Open source
    • Security
  15. One MCP server for PayStage's payment, approval, trade and velocity checks

    Runs locally
    • 4 tools
    • Open source
    • Finance and payments
  16. Check an x402 payment request against a local spending policy before your agent pays

    Runs locally
    • Open source
    • Finance and payments
  17. Check HIP-3 and trade.xyz orders against a local trade policy before an agent trades

    Runs locally
    • 1 tool
    • Open source
    • Finance and payments
  18. Rust MCP server for UniFi controllers with scoped tools and two-person change control

    Runs locally
    • 5 tools
    • Open source
    • Cloud and infrastructure
  19. Federate agent tools and MCP servers behind one governed gateway with routing and failover

    Not checked yet
    • Remote
    • Paid
    • Developer tools
  20. Let an agent browse sites where you are already logged in, with encrypted local sessions

    Not checked yet
    • 3 tools
    • Remote
    • Free
    • Browser automation
  21. Scan text, tool output and web pages for prompt injection, secrets, PII and SSRF URLs

    Not checked yet
    • 1 tool
    • Remote
    • Freemium
    • Security
  22. Check, test and review row-level security policies for Postgres from a coding agent

    Runs locally
    • 4 tools
    • Open source
    • Databases
  23. Run MCP servers with a scoped environment, audit trail and discovery from registries

    Runs locally
    • Open source
    • Security
  24. Run an agent's code and shell commands in a locked-down Docker workspace

    Runs locally
    • 6 tools
    • Open source
    • Developer tools
  25. Give an AI agent the SMS verification codes that arrive on your iPhone

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Communication
  26. Offline security checks for code, dependencies and AI agent setup with six read-only tools

    Runs locally
    • Open source
    • Security
  27. Search, read and write a folder of Markdown notes with hybrid keyword and meaning search

    Not checked yet
    • 14 tools
    • Remote
    • Free
    • Files and documents
  28. Pre-payment check for AI agents: allow, hold or block, with a signed attestation

    Not checked yet
    • 1 tool
    • Remote
    • Freemium
    • Finance and payments

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