Inference hooks
A Claude Enterprise feature, in beta, that sends each governed request to the organization's own AI security server before inference runs and waits for an allow or deny verdict; a denied request never reaches the model. With tool-call validation turned on, the tool calls in a response are sent as well, before any of them runs. It runs on Anthropic's servers, so nothing is installed on devices, and it never receives system prompts or raw file bytes.
How MoorAI handles it: moorai-inference-hook is a security server for Inference hooks: it verifies each signed request and answers allow or deny.
See also agent hook · model proxy · PreToolUse hook
Sources
Related terms
-
Agent hook
Agents & architecture
A command an agent host runs at fixed points in its loop — before a tool call, after a tool call, when a prompt is submitted, when a session starts or…
-
Model proxy
Agents & architecture
A service between an application or agent and its model provider's API: the client points its base URL at the proxy, which forwards each request and can…
-
PreToolUse hook
Agents & architecture
A callback the agent host invokes after the model has requested a tool call but before the call executes, handing over the tool name and arguments and…
Agents & architecture
Where the attacks above actually land. The vocabulary here is worth precision, because the difference between "the model decided" and "the tool ran" is the difference between a risk and an incident.