Connect Databricks to GitHub Copilot
Give GitHub Copilot governed access to Databricks through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add Databricks to GitHub Copilot in four steps
Admins approve the server once. Everyone in GitHub Copilot then gets it through the same governed connection.
- 1
Add Databricks to Runlayer
Databricks isn’t in the Runlayer catalog yet, so an admin adds it by its MCP server URL.
Adding a connector manually - 2
Connect GitHub Copilot to Runlayer
GitHub Copilot gets connector tools through the Runlayer Plugin, and reaches Databricks’s tools through the plugin’s search and execute tools.
GitHub Copilot setup guide - 3
Sign in to Databricks
Sign in the way Databricks requires. Runlayer holds the credentials so they stay out of the client’s configuration.
- 4
Use Databricks from GitHub Copilot
Databricks’s approved tools appear in GitHub Copilot. Every call is checked against policy and recorded.
Tools
Databricks tools in GitHub Copilot
Databricks reports its tools when your organization connects it, so the list depends on your deployment.
Control
What Runlayer can see and stop in GitHub Copilot
Some controls apply to every client at the gateway. Others depend on what GitHub Copilot exposes to Runlayer.
Gateway policy (available)
Every Databricks call from GitHub Copilot passes through Runlayer, where your policies can allow, alert, mask, or block it.
Audit trail (available)
Each call is recorded with the user, GitHub Copilot as the client, the tool, and the policy and scanner decisions.
Native enforcement adapter (not available)
Runlayer has no device-side adapter for GitHub Copilot yet, so control happens at the gateway.
Frequently asked questions
Connect more