<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/e71a620693d24c298f43f526987e2d4b&quot; frameborder=&quot;0&quot; width=&quot;1114&quot; height=&quot;835&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>835</height><width>1114</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>835</thumbnail_height><thumbnail_width>1114</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/e71a620693d24c298f43f526987e2d4b-8801fa63b50f674d.gif</thumbnail_url><duration>296.549</duration><title>Kilo Code - Cost insights MCP and Auto model visibility</title><description>This Loom demonstrates a cloud dashboard MCP that any agent can use to query and analyze cloud costs. The author shows authenticating via a CLI and then using the connected dashboard data to request per model breakdowns and usage by domain, plus outliers and graphs, including in cloud agent sessions. They note the MCP can be integrated into cost insights or expanded to control more of the dashboard and access logs. The Loom also mentions another feature for showing the underlying auto routing model, for example AutoBalanced selecting Qwen3, with each step displaying the chosen model.</description></oembed>