Azure Web PubSub Agentic Access
Azure Web PubSub exposes 19 API operations that an AI agent could call, of which 15 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.
By consequence: 4 read, 10 write, 4 physical, and 1 safety-critical.
1 operation are classed safety-critical and should require human-in-the-loop approval at runtime.
Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.
By consequence
Highest-consequence actions
The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.
| Method | Path | Consequence | Human-in-loop |
|---|---|---|---|
| DELETE | /api/hubs/{hub}/permissions/{permission}/connections/{connectionId} | safety-critical | required |
| POST | /api/hubs/{hub}/:send | physical | conditional |
| POST | /api/hubs/{hub}/connections/{connectionId}/:send | physical | conditional |
| POST | /api/hubs/{hub}/groups/{group}/:send | physical | conditional |
| POST | /api/hubs/{hub}/users/{userId}/:send | physical | conditional |