Skip to main content
Manage the full lifecycle of Wherobots notebook workspaces without leaving VS Code. The Wherobots extension lets you create, start, stop, and dismiss workspaces from the sidebar, and automatically connects your local Jupyter notebooks to remote Wherobots compute with kernel selection. For installation and configuration, see Wherobots VS Code Extension Setup. For specific tasks, see:

​
Start a workspace

The extension can create and start Wherobots workspaces directly from VS Code.
  1. Open the Wherobots sidebar in VS Code.
  2. Click the button to create a new workspace.
  3. Choose the runtime configuration for your workspace.
  4. Wait for the workspace to provision. The extension displays status updates as the workspace starts.
You can also create a workspace from the Command Palette (⌘ + ⇧ + P on Mac, Ctrl + Shift + P on Windows/Linux) by running Wherobots: Create Workspace. Once the workspace is running, the extension automatically detects available kernels so you can create and connect local Jupyter notebooks to the remote Wherobots runtime.
Workspace startup time varies by runtime size. Larger runtimes may take several minutes to provision.

​
Destroy a workspace

Stopping a workspace destroys your runtime in Wherobots, halting compute billing. You can start a new workspace later to resume work. To stop running workspaces:
1
Open Command Palette and run Wherobots: Focus on Workspaces View.
2
Find the workspace you want to destroy.
3
Click the square button .
4
Confirm that you want to stop the workspace. Stopping a workspace stops compute. You can restart the workspace later to resume work.

​
Other actions

The following actions are available for each workspace in the sidebar by right clicking on a running notebook workspace:
ActionDescription
Connect KernelConnect the selected running workspace to a notebook kernel
Stop WorkspaceStop a running or starting workspace
Open in BrowserOpen the workspace in the Wherobots Cloud Console
Open Spark UIOpen the Spark UI for a running workspace (when available)
Copy Jupyter URLCopy the workspace Jupyter endpoint
DismissHide a failed workspace entry from the sidebar
You can also run Wherobots: Refresh Workspaces from the Command Palette to refresh the workspace list. Stopping a workspace destroys your runtime in Wherobots, halting compute billing while preserving the workspace configuration. You can start a new workspace later to resume work. You can also manage workspaces from the Wherobots Cloud Console.

​
Automatic MCP server configuration

The Wherobots VS Code extension automatically configures the Wherobots MCP Server in VS Code, providing one-click setup for AI-assisted development. Once configured, you can:
  • Explore spatial data catalogs through GitHub Copilot Chat
  • Generate, validate, and execute Spatial SQL queries using natural language
  • Discover dataset schemas without writing code
No manual MCP server configuration is required when using the extension. For advanced MCP server options, see Configure Wherobots MCP Server.

​
Cost considerations

Consider the following cost implications when using the Wherobots VS Code extension:
  • Workspaces and kernels: Running workspaces consume Spatial Units (SUs) for the duration they are active. Stop workspaces when not in use.
  • Job runs: Billed based on runtime size and duration. See Runtimes for pricing details.
  • MCP server queries: SQL Sessions started by MCP queries run on a Tiny runtime and terminate after 5 minutes of inactivity. See MCP Usage Considerations.
  • Copilot usage: AI interactions count toward your GitHub Copilot usage limits. See Copilot Requests in the GitHub Documentation.

​
Troubleshooting

If you encounter issues with the Wherobots VS Code extension, try the following troubleshooting steps:
  • Verify the extension was installed successfully by checking the Extensions view for Spatial AI Coding Assistant by Wherobots
  • Reload VS Code (Command Palette > Reload Window)
  • Reinstall the extension from the VS Code Marketplace
  • Confirm the workspace status is running
  • Try Wherobots: Refresh Workspaces from the Command Palette and reconnect from the kernel picker
  • Ensure Jupyter integration is enabled: wherobotsjobsubmit.jupyterIntegrationEnabled
  • Review the VS Code Output panel for connection error details
  • Verify your API key has permissions to submit jobs
  • Check that the script path is valid and the file is accessible
  • Review the VS Code Output panel for error details
  • Confirm your Organization has sufficient Spatial Unit allocation
  • Ensure Agent mode is selected in the Copilot Chat dropdown
  • Verify the MCP server is running (Command Palette > MCP: List Servers)
  • Confirm wherobotsjobsubmit.mcpServerEnabled is true in VS Code Settings
  • Check that your API key is valid and re-check optional MCP runtime/region/timeout settings
  • Start a new chat session if tools are not being discovered