BigQuery MCP server

Integrates with BigQuery to enable querying and retrieving table schemas from specified datasets for data analysis and reporting
Back to servers
Provider
monochromegane
Release date
Feb 09, 2025
Language
Go

MCP BigQuery Server is a lightweight tool that enables querying BigQuery tables using the Model Context Protocol (MCP). It provides a simple interface to interact with BigQuery datasets and tables through various commands, making it easier to work with BigQuery data.

Installation

You can install MCP BigQuery Server using Homebrew:

brew tap monochromegane/tap
brew install monochromegane/tap/mcp-bigquery-server

Usage

Available Tools

MCP BigQuery Server provides several tools for interacting with BigQuery:

  • list_allowed_datasets: Get a listing of all allowed datasets.
  • list_tables: Get a detailed listing of all tables in a specified dataset.
  • get_table_schema: Get the schema of a specified table in a specified dataset.
  • dry_run_query: Dry run a query to get the estimated cost and time.

Configuration with Cursor

To use MCP BigQuery Server in Cursor, add the following configuration to your .cursor/mcp.json file:

{
  "mcpServers": {
    "BigQuery": {
      "command": "mcp-bigquery-server",
      "args": [
        "start",
        "--project",
        "sample-project",
        "--dataset",
        "test1",
        "--dataset",
        "test2"
      ]
    }
  }
}

Multiple Dataset Configuration

You can specify multiple datasets by repeating the --dataset argument:

mcp-bigquery-server start --project your-project --dataset dataset1 --dataset dataset2 --dataset dataset3

This allows you to access multiple BigQuery datasets through a single MCP server instance.

Starting the Server

To start the MCP BigQuery Server, use the following command:

mcp-bigquery-server start --project your-project-id --dataset your-dataset-name

Replace your-project-id with your actual Google Cloud project ID and your-dataset-name with the BigQuery dataset you want to access.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later