CA Data Agent MCP Server Setup Guide

1. Go to Settings > Apps > Create app
2. Enter the Server URL:
   https://bigquery.googleapis.com/mcp
3. Configure OAuth using credentials from the JSON file downloaded in Step #1:
   • Client ID: client_id field
   • Client Secret: client_secret field
4. Save and connect to login with Google

Gemini CLI uses a local settings file for MCP configuration. It uses google_credentials auth provider to send OAuth tokens from your local Google Cloud credentials to MCP servers.

1. Create or edit the settings file at one of these locations:
   • User-level: ~/.gemini/settings.json (applies to all projects)
   • Project-level: .gemini/settings.json in your project root (overrides user settings)
2. Add the BigQuery MCP server configuration:

   {
     "mcpServers": {
       "bigquery": {
         "httpUrl": "https://bigquery.googleapis.com/mcp",
         "authProviderType": "google_credentials",
         "oauth": {
           "scopes": [
             "https://www.googleapis.com/auth/bigquery",
             "https://www.googleapis.com/auth/cloud-platform"
           ]
         }
       }
     }
   }

3. Ensure you're authenticated with Google Cloud:

   gcloud auth application-default login

4. Restart Gemini CLI to load the new configuration

Gemini CLI requires a different approach using bearer token headers (unlike the BigQuery server which uses google_credentials):

1. Add the CA Agent MCP server to your settings file alongside the BigQuery server:

   "dataagents": {
     "httpUrl": "https://mcp.cademo.dev/{project}/dataagents/mcp",
     "headers": {
       "Authorization": "Bearer ${MCP_ACCESS_TOKEN}"
     }
   }

   Copy Config
2. Start Gemini CLI with your access token:

   MCP_ACCESS_TOKEN=$(gcloud auth print-access-token) gemini