Authorisation
2 posts
20 min read
OAuth scopes weren't built for AI agents: the delegation model that holds up under prompt injection
OAuth scopes assume a human approves once, an app does narrow work, and the trust horizon is months. AI agents break every part of that assumption. The architecture that holds is a two-principal model with short-lived delegation tokens, ReBAC for structure, ABAC for context, and per-action consent gating destructive operations. Here is the design and the rollout.
- AI agents
- Authorisation
- ReBAC
3 min read
MCP and the new authorisation surface nobody is reviewing
Model Context Protocol turns every internal API into a tool an agent can call on a user's behalf. The authorisation model most teams ship with is naïve, and the audit log usually proves it.
- MCP
- Agents
- Authorisation
Get started
Talk to the security lead who would do the work.
A thirty-minute discovery call costs nothing. We confirm fit, scope, and timing, then issue a fixed-fee statement of work within two business days.