Skip to content

MCP servers for security

152 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. Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  2. Self-assess AI agent governance: A3 scorecard, ISO 42001 evidence and PII scan

    Runs locally
    • 6 tools
    • Open source
    • Security
  3. Gateway that verifies what an MCP server really does, then confines every call

    Runs locally
    • Open source
    • Security
  4. Scan prompts for injection and PII, and audit LLM SDK usage from an MCP client

    • 13 tools
    • Remote
    • Freemium
    • Security
  5. Gate every MCP tool call behind signed authorization and single-use capabilities

    Runs locally
    • Open source
    • Security
  6. Browser actions for AI agents that are classified, approved and logged

    Runs locally
    • 1 tool
    • Open source
    • Browser automation
  7. MCP wrapper that holds database writes until a second person approves them on their phone

    Runs locally
    • Open source
    • Databases
  8. Read-only Trino access for agents, run as the verified user so Trino policy decides

    Runs locally
    • 3 tools
    • Open source
    • Databases
  9. Rank security scanner findings by exposure, criticality and exploitability

    Runs locally
    • Open source
    • Security
  10. Keep API keys in your OS keychain and give coding agents only what policy allows

    Runs locally
    • Open source
    • Security
  11. Local anonymiser that swaps client names and amounts for codes before Claude reads files

    Runs locally
    • Free trial
    • Security
  12. Open-source MCP gateway that pins tools, holds risky calls and limits egress

    Runs locally
    • Open source
    • Security
  13. Policy-gated agent spending with signed receipts and audit against the payment rail

    Runs locally
    • 5 tools
    • Open source
    • Finance and payments
  14. Checks JS/TS written by AI for risky patterns, fake npm packages and weakened tests

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  15. Agents use your API keys, SSH keys and wallets via a local broker and never hold them

    Runs locally
    • 10 tools
    • Free
    • Security
  16. Sealed microVM sandboxes for agents to run untrusted code, locally or in the cloud

    Not checked yet
    • Remote
    • Free trial
    • Developer tools
  17. Local deterministic security scan of your workspace with fix guidance for your AI agent

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

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

    Runs locally
    • Open source
    • Developer tools
  20. Pseudonymise or redact German court rulings and filings locally before AI sees them

    Runs locally
    • Paid
    • Legal and government
  21. Guard that checks MCP tool calls against a passkey-signed permission and logs receipts

    Runs locally
    • Free
    • Security
  22. Gateway that checks agent tool calls against signed grants and records signed receipts

    Runs locally
    • Freemium
    • Security
  23. 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
  24. Local permission gate that allows or stops an agent's tool call before it runs

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

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

    Runs locally
    • Open source
    • Security
  27. Run compliance readiness scans on your code from Claude Code, Cursor or Codex

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

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

    Runs locally
    • 2 tools
    • Open source
    • Cloud and infrastructure

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