Skip to content

MCP servers for security

419 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. Local, reversible masking of client names and numbers before text goes to an AI

    Runs locally
    • Open source
    • Security
  2. Real-time alerts for deepfake voices, impersonation and social engineering on live calls

    Not checked yet
    • Remote
    • Contact sales
    • Security
  3. Open-source MCP gateway that pins tools, holds risky calls and limits egress

    Runs locally
    • Open source
    • Security
  4. Open-source MCP server scoring pull-request risk from blast radius and git history

    Runs locally
    • 4 tools
    • Open source
    • Developer tools
  5. Open-source control plane that firewalls MCP tool calls and caps agent model spend

    • Remote
    • Open source
    • Security
  6. Policy-gated agent spending with signed receipts and audit against the payment rail

    Runs locally
    • 5 tools
    • Open source
    • Finance and payments
  7. MSP-focused MCP server and CLI for WatchGuard Cloud across customers

    Runs locally
    • Open source
    • Security
  8. Read-only payment preflight for AI agents: pay, review or do-not-pay before signing

    • 9 tools
    • Remote
    • Open source
    • Security
  9. Checks JS/TS written by AI for risky patterns, fake npm packages and weakened tests

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  10. Check an AI agent's action against signed rules before it commits, with auditable proof

    • 7 tools
    • Remote
    • Free trial
    • Security
  11. Give each AI agent its own inbox, saved logins and 2FA codes

    • Remote
    • Free trial
    • Security
  12. Run an 88-test MCP spec compliance suite and get an A-F grade from CLI or agent

    Runs locally
    • 2 tools
    • Open source
    • Security
  13. Local input firewall that scans text, files and MCP metadata for prompt injection

    Runs locally
    • Open source
    • Security
  14. Sealed microVM sandboxes for agents to run untrusted code, locally or in the cloud

    Not checked yet
    • Remote
    • Free trial
    • Developer tools
  15. Electron IPC scaffolding, security audits, CSP and build-error diagnosis for assistants

    Runs locally
    • 8 tools
    • Open source
    • Developer tools
  16. Lint CLAUDE.md, AGENTS.md and .mcp.json against your actual codebase

    Runs locally
    • Open source
    • Developer tools
  17. npm registry intelligence, security audits and publish-side writes without the 2FA prompt

    Runs locally
    • 9 tools
    • Open source
    • Developer tools
  18. Screen an x402 payment counterparty with allow, review or block before an agent pays

    Runs locally
    • 1 tool
    • Open source
    • Security
  19. Checks an x402 payment against your spending policy and returns pay, review or block

    Runs locally
    • Open source
    • Finance and payments
  20. Flags fake engagement and prompt injection in AI-agent job board listings

    Runs locally
    • Open source
    • Security
  21. Open-source scheduler that runs coding agents in parallel under policy-as-code rules

    Runs locally
    • Open source
    • Developer tools
  22. Local application security scanner with an evidence ledger and honest gap reporting

    Runs locally
    • Open source
    • Security
  23. Checks an agent's PR handback claims against GitHub's own record with no model involved

    Runs locally
    • Open source
    • Developer tools
  24. 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
  25. Local permission gate that allows or stops an agent's tool call before it runs

    Runs locally
    • Open source
    • Security
  26. Audit remote MCP servers for OAuth 2.1 gaps, and generate tested connectors

    Runs locally
    • Open source
    • Security
  27. Kubernetes MCP server where every change needs a passkey approval from your phone

    Runs locally
    • Open source
    • Cloud and infrastructure

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