Install MCP Server

​

Benefits

• Intelligent Catalog Exploration: Discover and understand your available datasets through natural language queries
• Data Quality Assessment: Query and evaluate the quality of your spatial data with AI assistance
• Pre-work Automation: Streamline initial spatial catalog exploration and analysis tasks
• Geospatial Query Assistance: Get help with spatial SQL queries and general geospatial questions

​

Before you start

• An Account within a Professional or Enterprise Organization. For more information, see Create a Wherobots Account.
  • Both Admin and User roles have access to MCP Server in Wherobots Cloud.
• A Wherobots API key. For more information, see API Keys.
• Visual Studio Code (VS Code) with GitHub Copilot and GitHub Copilot Chat..
  • For more information on downloading and installing GitHub Copilot, see GitHub Copilot for VS Code in the VS Code Documentation.
  • For more information on using GitHub Copilot, see Get started with chat in VS Code in the VS Code Documentation.
  Using the MCP server may result in data flowing to some of our services that are hosted in the United States. This may impact data residency for non-US customers.
  Using the MCP Server with advanced AI models like Claude Sonnet 4 or GPT-4 is recommended for optimal performance.

​

Enable Wherobots MCP Settings in VS Code

1. Log in to GitHub Copilot.
2. Open your VS Code Settings (e.g., press Cmd+, on Mac).
3. In the search bar, type mcp.
4. Configure the following settings:
   • Chat Mcp Discovery: Enabled
   • Chat > Mcp > Access: all
   • Chat > Mcp > Autostart: newAndOutdated

​

Add the Wherobots MCP server

1. Open the VS Code Command Palette (e.g., press Cmd+Shift+P on Mac).
2. Type MCP: Add Server and select it from the list.
3. You will be prompted to “Choose the type of MCP server to add”. Select HTTP (HTTP or Server-Sent Events).
4. When prompted for the URL, enter the service URL: https://api.cloud.wherobots.com/mcp/.
5. When prompted, provide a name for your MCP server (e.g., “wherobots-mcp-server”).

​

Configure mcp.json

1. Your mcp.json file will open automatically after adding the server. If not, you can open it manually by typing and selecting >mcp: Open User Configuration in the Command Palette.
2. Add a "headers" object containing your "x-api-key", using your Wherobots API key as the value. Copy and paste the following into your mcp.json, replacing the placeholders with your chosen MCP server name and Wherobots API key.
   Report incorrect code

   Copy

   Ask AI

   "servers": {
     "<YOUR-MCP-SERVER-NAME-HERE>": {
       "url": "https://api.cloud.wherobots.com/mcp/",
       "type": "http",
       "headers": {
         "x-api-key": "<YOUR-WHEROBOTS-API-KEY-HERE>"
       }
     }
   }
   
3. Save the mcp.json file.
4. Reload VS Code to apply your changes:
   1. Open the Command Palette (Cmd+Shift+P on Mac, Ctrl+Shift+P on Windows/Linux).
   2. Type and select Reload Window.
5. Open the Command Palette again and type MCP: List Servers.
   1. Select your server from the list, then click Start Server.
   2. Check the VS Code Output panel to confirm the server has started successfully.
   To find the Output Panel, go to the menu and select View > Output. You should see log entries similar to the following:
   Report incorrect code

   Copy

   Ask AI

   2025-11-14 14:12:46.829 [info] Starting server wherobots-mcp-server
   2025-11-14 14:12:46.831 [info] Connection state: Starting
   2025-11-14 14:12:46.831 [info] Starting server from LocalProcess extension host
   2025-11-14 14:12:46.833 [info] Connection state: Running
   2025-11-14 14:12:47.953 [info] Discovered 8 tools
   

​

Verify the connection

1. Open the GitHub Copilot Chat view. To do this, click View > Chat from the VS Code menu bar on your Mac or Windows/Linux system.
2. If you haven’t already, click New Chat (Cmd+N on Mac or Ctrl+N on Windows/Linux) button to start a new chat session.
3. Make sure you have Agent selected as the chat mode. You can select this from the dropdown menu at the top of the chat panel.
4. You can also select the model you wish to use alongside the MCP server from the adjacent dropdown. Quality of responses may vary between models.
   Wherobots recommends using advanced models like Claude Sonnet 4 or GPT-4 for optimal performance with the MCP server.
5. Ask a question to see if it interacts with the Wherobots service, for example:

   Show me the catalogs in my Organization

6. If successful, Copilot will confirm it is using the Wherobots MCP server (showing Ran list_catalogs or a similar tool) and display all of the available catalogs in your Organization. The exact response will vary depending on the datasets within your Organization as well as the model used to query the MCP server. At minimum, wherobots_open_data appears for Community Edition, and both wherobots_open_data and wherobots_pro_data for Professional and Enterprise Edition Organizations.

​

Next steps and best practices

​

Stop the MCP Server

1. Open the Command Palette (Cmd+Shift+P on Mac, Ctrl+Shift+P on Windows/Linux).
2. Type and select MCP: List Servers.
3. Select the name of your server from the list.
4. Click Stop Server.