drio
Open app

BigQuery MCP Server

Source

A Model Context Protocol (MCP) server that provides secure, read-only access to BigQuery datasets. Enables Large Language Models (LLMs) to safely query and analyze data through a standardized interface.

Catalog onlyCatalog onlySTDIO

Overview

BigQuery MCP Server is a Model Context Protocol (MCP) server that provides secure, read-only access to BigQuery datasets, allowing Large Language Models (LLMs) to query and analyze data through a standardized interface.

To use the BigQuery MCP Server, set up authentication, add your Google Cloud project details to Claude Desktop's configuration, and start chatting with your BigQuery data using plain English queries.

  • Run SQL queries by asking questions in natural language. - Access both tables and materialized views in datasets. - Explore dataset schemas with clear labeling. - Analyze data within a 1GB query limit, ensuring data security with read-only access.
  1. Querying sales data to find trends.
  2. Analyzing customer behavior through BigQuery datasets.
  3. Generating reports by simply asking about the data.

Add to your AI client

Use these steps to connect BigQuery MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-bigquery-server-ergut": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bigquery-server-ergut"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-bigquery-server-ergut": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bigquery-server-ergut"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-bigquery-server-ergut": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bigquery-server-ergut"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-bigquery-server-ergut": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bigquery-server-ergut"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-bigquery-server-ergut": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bigquery-server-ergut"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-bigquery-server-ergut": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bigquery-server-ergut"
      ]
    }
  }
}

FAQ

What LLMs can use the MCP Server?

Currently, it is designed for use with Claude Desktop.

Is there a limit on query size?

Yes, there is a 1GB processing limit per query.

Can I modify the data in BigQuery?

No, the server provides read-only access for security.