<?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/b4f4d89cc9494a85a488da1905ca3a79&quot; frameborder=&quot;0&quot; width=&quot;1662&quot; height=&quot;1246&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1246</height><width>1662</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1246</thumbnail_height><thumbnail_width>1662</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b4f4d89cc9494a85a488da1905ca3a79-fd2c794d71bce19d.gif</thumbnail_url><duration>377.779</duration><title>Connect Thunk to Databricks SQL Tools 🔗</title><description>I walk through connecting Thunk to my Databricks SQL MCP server using an authorization header with a Bearer token. In Thunk, I add a custom connection named Databricks Salesforce Accounts, then select the execute SQL read-only tool for safety. I run a sample SQL query and confirm it returns JSON results, then use the tool builder to wrap that SQL into a custom AI tool. The tool smoke-tested successfully and returned 13 account rows. No viewer action was explicitly requested.</description></oembed>