<?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/34587e618c5c47c0b0d67b4e4d02718f&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/34587e618c5c47c0b0d67b4e4d02718f-b56c71f82478781d.gif</thumbnail_url><duration>156.571</duration><title>LiteLLM Demo - Responses API + MCP Gateway</title><description>In this video, I demonstrate how to use MCP tools with the LightElem APIs, specifically focusing on the responses API and the Gemini model. I walk you through making a curl request to fetch data from our onboarded MCPs, DeepWiki and GitMCP, and show how to swap between different models like Bedrock. Additionally, I provide a Python example using the OpenAI SDK to illustrate how to execute requests and stream responses. I encourage you to explore these tools and try out the examples provided. Please make sure to familiarize yourself with the API functionalities for better integration into your projects.</description></oembed>