Blog

On permissioning AI, from the people building it.

Essays on agent security, MCP infrastructure, and what we learn shipping the gateway to production.

Articles

Latest

EssayJune 7, 20267 min read

Identity is the floor, not the ceiling. What non-human identities actually need in agentic AI.

Okta is right that non-human identities matter for agentic AI. But identity is the floor of the problem, not the ceiling — and the ceiling is where most of the actual risk lives.

By Timothé Husson BrombergRead the essay

How-to guideJune 7, 2026
How to secure tool access in an MCP hub. A practical six-step playbook for AI agent governance.
Identity, scope, payload constraints, replayable audit, policy-as-code, and adoption observability — distilled into something you can hand a platform engineer Monday morning.
EssayJune 5, 2026
Anthropic wrote the spec for agent identity. It reads like a build plan for a system most teams don’t have.
Page 9 of Anthropic’s Zero Trust for AI Agents quietly invalidates how most agent integrations work today. Here’s what the spec actually says, why most teams won’t build it, and where that gap has to live.
OpinionMarch 10, 2026
Why your AI agent needs guardrails before it needs tools.
MCP is connecting agents to every API on earth. Nobody’s asking what happens when they get it wrong. Policies, human-in-the-loop, and audit — the seatbelts the AI agent ecosystem still doesn’t have.

On permissioning AI, from the people building it.

Identity is the floor, not the ceiling. What non-human identities actually need in agentic AI.

How to secure tool access in an MCP hub. A practical six-step playbook for AI agent governance.

Anthropic wrote the spec for agent identity. It reads like a build plan for a system most teams don’t have.

Why your AI agent needs guardrails before it needs tools.

See Hodor on your stack.