Agent Security
Agent Security gives you visibility and control over what AI agents can do in your organization. It sits between your team's AI tools (like Cursor, Claude, and VS Code) and the services they connect to, enforcing who can access what, logging every action, and letting you set guardrails — all without changing your existing tools or code.
Prerequisites
- A Permit.io account (free tier available)
- Access to the Agent Security Platform — the admin dashboard where you create hosts, import MCP servers, manage users, and monitor activity
What You Get
- Control what agents can do — Set per-tool permissions with trust levels (read-only, write, destructive) so agents only access what they need
- See everything agents do — Every tool call is logged with who did it, what they did, and whether it was allowed
- Enforce authentication — Require SSO, OAuth, or other sign-in methods before agents can access tools
- Human oversight — Users choose what level of access to grant their agents through a consent flow
Start Here
- Read the Overview to understand what Agent Security is and how it works
- Follow the Getting Started Guide to set up your first gateway in minutes
Go Deeper
- Platform Reference — Admin UI guide for managing hosts, servers, and users
- Humans & Agents — Managing users and the AI agents acting on their behalf
- Host Setup Guide — Multi-host patterns and onboarding users at scale
- Authentication Methods — SSO, OAuth, and sign-in configuration
- Consent Service — The user consent journey in detail
- Audit Logs — Reading and using activity logs
- Architecture Deep Dive — Technical architecture, data flows, and sequence diagrams
- Permit.io Integration Deep Dive — Policy engine internals and authorization model
- Advanced Features — Enterprise capabilities: agent fingerprinting, shadow agent detection, HITL approvals, intent-based access control, permission receipts, and more
Support and Resources
- Join our Slack Community for discussions and updates
- Access the Permit.io API Reference for the underlying authorization API
- Contact Support for direct assistance