Skip to content

AI for security

181 AI tools, agents, MCP servers and skills for security, with pricing, platforms and alternatives for each.

Showing 1–30 of 181

  1. pentagi

    Agent

    Self-hosted multi-agent system that plans and runs penetration tests in a sandbox

    • Open source
    • Open-source agent
    • 34.3K GitHub stars
    • Security
  2. Rust agent operating system with scheduled autonomous Hands and a WASM sandbox

    • Open source
    • Open-source agent
    • 18.3K GitHub stars
    • Multi-agent frameworks
  3. Microsoft toolkit for policy enforcement, identity and audit of autonomous agents

    • Open source
    • Open-source agent
    • 6.6K GitHub stars
    • Security
  4. Open-source gateway adding identity, policy and audit between AI agents and your systems

    • Open source
    • Open-source agent
    • 4.4K GitHub stars
    • Security
  5. Midplane

    MCP server

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

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

    Runs locally
    • 6 tools
    • Open source
    • Security
  7. WhoisFreaks

    MCP server

    WHOIS, DNS, IP, SSL and domain lookups from WhoisFreaks, as 22 read-only tools

    • 22 tools
    • Remote
    • Freemium
    • Security
  8. Gateway that verifies what an MCP server really does, then confines every call

    Runs locally
    • Open source
    • Security
  9. Zeqqat

    MCP server

    A safer MCP for Dokploy: agents deploy and fix apps without seeing keys or secrets

    Not checked yet
    • 8 tools
    • Remote
    • Open source
    • Cloud and infrastructure
  10. PromptGuard

    MCP server

    Scan prompts for injection and PII, and audit LLM SDK usage from an MCP client

    • 13 tools
    • Remote
    • Freemium
    • Security
  11. Automata

    MCP server

    Give AI agents WhatsApp, Telegram and PostgreSQL access limited by explicit scopes

    Not checked yet
    • 4 tools
    • Remote
    • Freemium
    • Communication
  12. Gate every MCP tool call behind signed authorization and single-use capabilities

    Runs locally
    • Open source
    • Security
  13. Ghost Hands

    MCP server

    Browser actions for AI agents that are classified, approved and logged

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

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

    Runs locally
    • 3 tools
    • Open source
    • Databases
  16. Draugr

    MCP server

    Rank security scanner findings by exposure, criticality and exploitability

    Runs locally
    • Open source
    • Security
  17. q-ring

    MCP server

    Keep API keys in your OS keychain and give coding agents only what policy allows

    Runs locally
    • Open source
    • Security
  18. MCP Hangar

    MCP server

    Open-source MCP gateway that pins tools, holds risky calls and limits egress

    Runs locally
    • Open source
    • Security
  19. Preloop

    MCP server

    Open-source control plane that firewalls MCP tool calls and caps agent model spend

    • Remote
    • Open source
    • Security
  20. Cedulon

    MCP server

    Policy-gated agent spending with signed receipts and audit against the payment rail

    Runs locally
    • 5 tools
    • Open source
    • Finance and payments
  21. AI Guard

    MCP server

    Checks JS/TS written by AI for risky patterns, fake npm packages and weakened tests

    Runs locally
    • 1 tool
    • Open source
    • Developer tools
  22. Sphior Code MCP

    MCP server

    Local deterministic security scan of your workspace with fix guidance for your AI agent

    Runs locally
    • 2 tools
    • Freemium
    • Security
  23. Bernstein

    MCP server

    Open-source scheduler that runs coding agents in parallel under policy-as-code rules

    Runs locally
    • Open source
    • Developer tools
  24. Dunstan

    MCP server

    Checks an agent's PR handback claims against GitHub's own record with no model involved

    Runs locally
    • Open source
    • Developer tools
  25. agent-custody

    MCP server

    Gateway that checks agent tool calls against signed grants and records signed receipts

    Runs locally
    • Freemium
    • Security
  26. Probarion

    MCP server

    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
  27. Local permission gate that allows or stops an agent's tool call before it runs

    Runs locally
    • Open source
    • Security