Blog
Notes on governing AI agents
Write agent policies for the groups you already have
Groups in Gatehouse, synced from Active Directory, LDAP, SCIM or SSO, so AI agent access follows your org chart.
ReadSelf-hosting Gatehouse for regulated teams
Running an MCP gateway inside your own network, with your own keys and your own logs.
ReadTool poisoning and rug pulls, explained
How MCP tool descriptions can carry hidden instructions, how a trusted server can change under you, and how Gatehouse defends against both.
ReadWhy every AI agent needs a front door
Agents act with real credentials on real systems. Here's why the control point belongs between them and your tools.
ReadIntroducing Gatehouse
One governed door between your team's AI agents and the systems they act on.
Read