Inside the policy engine: how Enforgate decides every tool call
A walkthrough of evaluate(): glob tool matching, param conditions, priority ordering, and why the engine default-denies when nothing matches.
Read more →Blog
Notes on agent security and MCP
Updates on Enforgate, and deeper looks at the action-boundary model behind it.
Announcing Enforgate: action-boundary security for AI agents
AI agents are starting to take real actions. Enforgate sits between agents and the tools they call, turning every action into a checked, audited decision.
Read more →