BigQuery

v1.0.4Databasesstable

Enables LLMs to interact with Google BigQuery by inspecting database schemas, listing tables, and executing SQL queries. This server facilitates seamless data analysis and management through natural language via the Model Context Protocol.

bigquerygoogle-cloudmcpmcp-serversmodel-context-protocol
Share:
139
Stars
0
Downloads
0
Weekly
0/5

What is BigQuery?

BigQuery is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables llms to interact with google bigquery by inspecting database schemas, listing tables, and executing sql queries. this server facilitates seamless data analysis and management through natural l...

Enables LLMs to interact with Google BigQuery by inspecting database schemas, listing tables, and executing SQL queries. This server facilitates seamless data analysis and management through natural language via the Model Context Protocol.

This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables LLMs to interact with Google BigQuery by inspecting

Use Cases

Execute SQL queries on BigQuery
Inspect database schemas and tables
Perform data analysis via natural language
ergut

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.4
UpdatedMay 14, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @ergut/mcp-bigquery-server

Manual Installation

npx -y @ergut/mcp-bigquery-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use BigQuery

The BigQuery MCP Server connects AI assistants like Claude directly to your Google BigQuery data warehouse, allowing you to query datasets, inspect schemas, and analyze data using plain English instead of writing SQL by hand. It is read-only by design — every statement is validated by BigQuery's dry-run planner before execution, so INSERT, UPDATE, DELETE, DROP, and MERGE are all blocked. It also supports field-level access restrictions to prevent AI agents from surfacing PII, PHI, or financial data into the LLM conversation context.

Prerequisites

  • Node.js 14 or higher installed
  • A Google Cloud project with BigQuery API enabled
  • Google Cloud CLI installed and authenticated via `gcloud auth application-default login`, or a service account key file
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Authenticate with Google Cloud

Use the Google Cloud CLI to set up application default credentials. This is the easiest method for local development.

gcloud auth application-default login
2

Add the server to your MCP client config

Open your MCP client configuration file (claude_desktop_config.json for Claude Desktop, or .mcp.json for Claude Code) and add the BigQuery server block, replacing `your-project-id` with your actual GCP project ID.

{
  "mcpServers": {
    "bigquery": {
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server",
        "--project-id",
        "your-project-id"
      ]
    }
  }
}
3

Optionally specify a region and billing limit

For production use or when your datasets live in a specific region, add the `--location` flag. You can also cap query costs with `--maximum-bytes-billed`.

npx -y @ergut/mcp-bigquery-server --project-id your-project-id --location us-central1
4

Use a service account for production deployments

For automated or server-based deployments, generate a service account key file from the GCP Console and pass it via the `--key-file` argument instead of relying on application default credentials.

{
  "mcpServers": {
    "bigquery": {
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server",
        "--project-id",
        "your-project-id",
        "--key-file",
        "/path/to/service-account-key.json"
      ]
    }
  }
}
5

Restart your MCP client and start querying

Restart Claude Desktop or your MCP client. The BigQuery server will start automatically. You can now ask questions about your data in natural language.

BigQuery Examples

Client configuration

Minimal Claude Desktop configuration using application default credentials.

{
  "mcpServers": {
    "bigquery": {
      "command": "npx",
      "args": [
        "-y",
        "@ergut/mcp-bigquery-server",
        "--project-id",
        "my-gcp-project-id"
      ]
    }
  }
}

Prompts to try

Natural language queries you can use once the server is connected.

- "What tables are available in the analytics dataset?"
- "Show me the top 10 customers by revenue last month"
- "What is the schema of the orders table?"
- "How many records does the events table have for this week?"
- "Summarize the sales by region for Q1 2024"

Troubleshooting BigQuery

Authentication error: Application Default Credentials not found

Run `gcloud auth application-default login` to set up credentials, or provide a service account key file with the `--key-file` argument.

Query is rejected with a mutation error even for SELECT statements

The server validates all queries with BigQuery's dry-run planner. Ensure your query does not contain any data manipulation keywords like INSERT, UPDATE, or CREATE. Only SELECT statements and reads from views are allowed.

Queries succeed but return no data or wrong datasets

Double-check the `--project-id` matches your GCP project and that the authenticated account has the BigQuery Data Viewer role on the relevant datasets.

Frequently Asked Questions about BigQuery

What is BigQuery?

BigQuery is a Model Context Protocol (MCP) server that enables llms to interact with google bigquery by inspecting database schemas, listing tables, and executing sql queries. this server facilitates seamless data analysis and management through natural language via the model context protocol. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install BigQuery?

Install via npm with the command: npx -y @ergut/mcp-bigquery-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with BigQuery?

BigQuery works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is BigQuery free to use?

Yes, BigQuery is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Databases MCP Servers

Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use BigQuery?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides