Skip to Content

BigQuery MCP Server

This guide walks through connecting the BigQuery MCP server to auxilia. BigQuery uses Google OAuth 2.0 with static credentials.

1. Create a Google Cloud OAuth Client

  1. Go to the Google Cloud Console 
  2. Select your project (or create a new one)
  3. Navigate to APIs & ServicesCredentials
  4. Click Create CredentialsOAuth client ID
  5. If prompted, configure the OAuth consent screen first:
    • User Type: External (or Internal for Google Workspace)
    • App name: auxilia MCP
    • Scopes: Add https://www.googleapis.com/auth/bigquery
  6. Back in Create OAuth client ID:
    • Application type: Web application
    • Name: auxilia MCP
    • Authorized redirect URIs: Add:
      https://your-auxilia-domain.com/mcp-servers/oauth/callback
      For local development:
      http://localhost:8000/mcp-servers/oauth/callback
  7. Click Create
  8. Copy the Client ID and Client Secret

2. Enable the BigQuery API

Make sure the BigQuery API is enabled for your project:

gcloud services enable bigquery.googleapis.com \ --project=your-project-id

3. Install the BigQuery MCP Server

In auxilia, navigate to MCP Servers:

  1. Find BigQuery in the official servers list
  2. Click Install
  3. Enter the credentials from your Google Cloud OAuth client:
    • Client ID: Your Google OAuth client ID
    • Client Secret: Your Google OAuth client secret

4. Connect Your Account

  1. Click the Connect button on the BigQuery server card
  2. You’ll be redirected to Google’s consent screen
  3. Select your Google account
  4. Grant BigQuery access permissions
  5. You’ll be redirected back to auxilia

auxilia automatically requests the https://www.googleapis.com/auth/bigquery scope.

5. Add to an Agent

  1. Navigate to an agent’s configuration page
  2. Click Add MCP Server
  3. Select BigQuery from the list
  4. Configure tool settings as needed

Available Tools

The BigQuery MCP server typically provides tools for:

  • Listing datasets and tables in a project
  • Querying data with SQL
  • Describing table schemas
  • Listing dataset IDs

Troubleshooting

”Access denied” error

Ensure that:

  • The BigQuery API is enabled in your Google Cloud project
  • Your Google account has BigQuery permissions in the target project
  • The OAuth consent screen includes the BigQuery scope

”Redirect URI mismatch”

The redirect URI in your Google Cloud OAuth client must exactly match:

https://your-auxilia-domain.com/mcp-servers/oauth/callback

Make sure there are no trailing slashes or protocol mismatches.

Last updated on