www.context-link.ai

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 description includes an instruction aimed at the AI ('the widget...does not show the retrieved content, so use the returned context to answer the user directly') rather than purely describing the tool's function. While this appears to be a legitimate UX note about the widget, embedding behavioral directives in tool descriptions is a known vector for prompt injection and should be scrutinized to ensure it isn't being used to make the agent disclose or act on hidden retrieved content without the user's awareness of the context's origin.

Similar to get_context, the description tells the agent to 'always relay the answer text in your reply' because the widget won't display it. This is likely benign functional guidance, but it is an instruction directed at the AI's behavior embedded in a tool description, which is a pattern worth monitoring for potential misuse in other contexts.