BigQuery MCP Server

What does “BigQuery” MCP Server do?

The BigQuery MCP Server is a Model Context Protocol (MCP) server that provides secure, read-only access to BigQuery datasets. It acts as a bridge between Large Language Models (LLMs) and your BigQuery data, allowing AI assistants to query and analyze data through a standardized interface. By translating natural language questions into SQL and managing database security, it enables developers and analysts to interact with their data conversationally—without the need for manual SQL. The server supports both tables and materialized views, offers schema exploration, and enforces safe query limits to protect your data. Its primary role is to enhance workflow efficiency by enabling LLMs to access business intelligence data securely and intuitively.

List of Prompts

No prompt templates are mentioned in the repository or documentation.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No specific MCP resources are documented in the repository or README.

List of Tools

No explicit tool list or server.py file is present in the available documentation or code structure.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Natural Language Data Exploration
  Users can ask questions in plain English (e.g., “What were our top 10 customers last month?”) and receive answers directly from BigQuery, reducing the need for manual SQL queries.

• Secure Business Intelligence
  Provides read-only access to sensitive datasets, enabling data analysts and business users to safely explore data without risk of modification.

• Schema Discovery
  Allows AI and users to explore dataset schemas, distinguishing between tables and views, streamlining the process of understanding available data structures.

• Data Analysis within Safe Limits
  Enforces query limits (e.g., 1GB by default), ensuring that resource usage is controlled and preventing accidental high-cost queries.

How to set it up

Windsurf

No setup instructions for Windsurf are provided in the repository.

Claude

1. Prerequisites:

   • Install Node.js 14 or higher.
   • Enable BigQuery in your Google Cloud project.
   • Install Google Cloud CLI or obtain a service account key file.
   • Install Claude Desktop.

2. Authenticate with Google Cloud:

   • For development:

     gcloud auth application-default login
     

   • For production (service account):
     • Save your service account key file.
     • Use the --key-file parameter when starting the server.

3. Add to Claude Desktop config:
   Edit your claude_desktop_config.json file:

   {
     "mcpServers": {
       "bigquery": {
         "command": "npx",
         "args": [
           "-y",
           "@ergut/mcp-bigquery-server",
           "--project-id",
           "your-project-id",
           "--location",
           "us-central1"
         ]
       }
     }
   }
   

4. Save and restart Claude Desktop.

5. Verify:
   Start a chat with Claude and ask a question about your data.

With service account:

{
  "mcpServers": {
    "bigquery": {
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server",
        "--project-id",
        "your-project-id",
        "--location",
        "us-central1",
        "--key-file",
        "/path/to/your/service-account-key.json"
      ]
    }
  }
}

Securing API Keys:
Store your service account key outside your repository and reference it via the --key-file parameter. Never commit keys to version control.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "bigquery": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “bigquery” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The BigQuery MCP Server provides a focused, secure, and user-friendly solution for connecting LLMs to BigQuery datasets. However, the repository currently lacks documentation for prompt templates, explicit MCP resources, and tool definitions, which would enhance extensibility and interoperability. The setup is straightforward for Claude Desktop, but instructions for other platforms (like Windsurf, Cursor, or Cline) or for advanced MCP features (roots or sampling) are missing. Overall, this MCP server is solid for its primary use case but limited in extensibility.

Rating: 6/10 — Great for its core job, but missing broader protocol features and documentation.

MCP Score