Local Agents
A local agent is a harness installed on a person's workstation that calls a cloud-hosted model. HYPR AgentPass™ governs it in two ways:
- The person onboards the agent, so its traffic is attributed to them.
- The Endpoint Guard on the workstation keeps that traffic on the gateway.
Give a Team Governed Coding Agents sequences the full rollout: connectors, roles, tools and mobile approvals.
The Endpoint Guard applies different controls to each supported tool.
| Tool | Routes inference through the gateway | Provisions your MCP connectors | Blocks direct provider egress |
|---|---|---|---|
| Claude Code | Yes | Yes | Yes |
| Codex CLI | Yes | Yes | Yes |
| Cursor | No | Yes | Yes |
| Claude Desktop | Yes | Yes | Yes |
For Cursor, the Endpoint Guard also observes the agent's actions through Cursor's own hooks.
You choose the managed tools, their inference routing and egress enforcement in Managed Desktop Tools. A tool that is not managed can still be pointed at the gateway by hand. See Onboarding Your Agent.
Switch a Local Agent Off
To stop a local agent, turn off its Active switch on Oversight → Agent identities. Switching it off from the HYPR mobile app, or removing its access in an access review, has the same effect.
- The gateway refuses the agent's next request, whichever connector it calls.
- The agent's messaging channel is disconnected.
- The agent stays off until someone turns it back on. Signing in to its AI provider again does not turn it back on. See Who Can Turn an Agent Off and On.
A request already in progress finishes. Traffic on a connector whose onboarding mode is Observe only is recorded and forwarded, not stopped. AWS Bedrock connectors are the exception: there, a switched-off developer's requests are refused. To keep a tool from reaching its provider directly, use egress enforcement.