api.autoview.com

This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.

The 'credentials' field accepts arbitrary string key/values and 'token' is a personal access token, both passed directly in the tool call. While likely necessary for functionality, this means sensitive secrets flow through the LLM context/transcript. Ensure these are not logged or echoed elsewhere, and that the agent isn't prompted to source these values from environment variables or files rather than explicit user-provided input.

The tool defaults to a safe dry-run but a single boolean 'live:true' triggers a real financial transaction. There's no enforcement in the schema requiring explicit user confirmation before setting live:true; an agent could be manipulated (via prompt injection elsewhere) into placing real orders. This is a design consideration rather than a malicious instruction, but worth flagging given real-money impact.