Overview
BigQuery MCP Server is a middleware that enables large language models (LLMs) like Claude to interact with BigQuery databases using natural language queries, eliminating the need for manual SQL coding.
To use the server, set up authentication, configure your project details in Claude Desktop, and start querying your BigQuery data by asking questions in plain English.
- Natural language querying of BigQuery data - Access to tables and materialized views - Clear dataset schema exploration - Secure read-only access with a 1GB query limit
- Querying customer data for insights
- Generating reports based on sales data
- Analyzing trends in large datasets
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": {
"ergut-mcp-bigquery-server-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-ergut-mcp-bigquery-server-mcp-mirror"
]
}
}
}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": {
"ergut-mcp-bigquery-server-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-ergut-mcp-bigquery-server-mcp-mirror"
]
}
}
}Claude Code
Add this to your project's .mcp.json file. Claude Code will detect it automatically.
.mcp.json (project root)
{
"mcpServers": {
"ergut-mcp-bigquery-server-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-ergut-mcp-bigquery-server-mcp-mirror"
]
}
}
}VS Code (Copilot)
Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.
.vscode/mcp.json
{
"servers": {
"ergut-mcp-bigquery-server-mcp-mirror": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-ergut-mcp-bigquery-server-mcp-mirror"
]
}
}
}Windsurf
Add this to your Windsurf MCP config file, then restart Windsurf.
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"ergut-mcp-bigquery-server-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-ergut-mcp-bigquery-server-mcp-mirror"
]
}
}
}Cline
Open Cline settings, navigate to MCP Servers, and add this server configuration.
Cline MCP Settings (via UI)
{
"mcpServers": {
"ergut-mcp-bigquery-server-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-ergut-mcp-bigquery-server-mcp-mirror"
]
}
}
}FAQ
Can I use it with any LLM?
Yes, it is designed to work with any AI model, but currently supports Claude Desktop.
Is there a limit on the data I can query?
Yes, there is a 1GB processing limit per query.
How do I set up authentication?
You can authenticate using Google Cloud CLI or a service account key file.