by ergut
mcp-bigquery-server is a Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to securely and efficiently interact with Google BigQuery datasets. It acts as a translator, allowing LLMs to query and analyze data in BigQuery using natural language instead of SQL.
mcp-bigquery-server is a Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to securely and efficiently interact with Google BigQuery datasets. It acts as a translator, allowing LLMs to query and analyze data in BigQuery using natural language instead of SQL.
There are two main ways to use mcp-bigquery-server:
npx @smithery/cli install @ergut/mcp-bigquery-server --client claude
gcloud auth application-default login
.--key-file
parameter.claude_desktop_config.json
file, replacing your-project-id
and optionally your-location
and /path/to/service-account-key.json
:
{
"mcpServers": {
"bigquery": {
"command": "npx",
"args": [
"-y",
"@ergut/mcp-bigquery-server",
"--project-id",
"your-project-id",
"--location",
"us-central1",
"--key-file",
"/path/to/service-account-key.json"
]
}
}
}
The server accepts the following arguments:
--project-id
: (Required) Your Google Cloud project ID.--location
: (Optional) BigQuery location (defaults to 'us-central1').--key-file
: (Optional) Path to service account key JSON file.Q: What are the prerequisites for using mcp-bigquery-server? A: Node.js 14 or higher, a Google Cloud project with BigQuery enabled, either Google Cloud CLI installed or a service account key file, and Claude Desktop.
Q: What are the current limitations of mcp-bigquery-server? A: MCP support is currently only available in Claude Desktop (developer preview), connections are limited to local MCP servers, queries are read-only with a 1GB processing limit, and some complex view types might have limitations.
Q: What permissions are needed for mcp-bigquery-server?
A: You'll need either roles/bigquery.user
or both roles/bigquery.dataViewer
and roles/bigquery.jobUser
.
Q: Can I contribute to mcp-bigquery-server? A: Yes, you can set up a developer environment by cloning the repository, installing dependencies, and building the project. You can then point your Claude Desktop config to your local build.
This is a server that lets your LLMs (like Claude) talk directly to your BigQuery data! Think of it as a friendly translator that sits between your AI assistant and your database, making sure they can chat securely and efficiently.
You: "What were our top 10 customers last month?"
Claude: *queries your BigQuery database and gives you the answer in plain English*
No more writing SQL queries by hand - just chat naturally with your data!
This server uses the Model Context Protocol (MCP), which is like a universal translator for AI-database communication. While MCP is designed to work with any AI model, right now it's available as a developer preview in Claude Desktop.
Here's all you need to do:
To install BigQuery MCP Server for Claude Desktop automatically via Smithery, run this command in your terminal:
npx @smithery/cli install @ergut/mcp-bigquery-server --client claude
The installer will prompt you for:
Once configured, Smithery will automatically update your Claude Desktop configuration and restart the application.
If you prefer manual configuration or need more control:
Authenticate with Google Cloud (choose one method):
gcloud auth application-default login
# Save your service account key file and use --key-file parameter
# Remember to keep your service account key file secure and never commit it to version control
Add to your Claude Desktop config
Add this to your claude_desktop_config.json
:
Basic configuration:
{
"mcpServers": {
"bigquery": {
"command": "npx",
"args": [
"-y",
"@ergut/mcp-bigquery-server",
"--project-id",
"your-project-id",
"--location",
"us-central1"
]
}
}
}
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/service-account-key.json"
]
}
}
}
Start chatting! Open Claude Desktop and start asking questions about your data.
The server accepts the following arguments:
--project-id
: (Required) Your Google Cloud project ID--location
: (Optional) BigQuery location, defaults to 'us-central1'--key-file
: (Optional) Path to service account key JSON fileExample using service account:
npx @ergut/mcp-bigquery-server --project-id your-project-id --location europe-west1 --key-file /path/to/key.json
You'll need one of these:
roles/bigquery.user
(recommended)roles/bigquery.dataViewer
roles/bigquery.jobUser
Want to customize or contribute? Here's how to set it up locally:
# Clone and install
git clone https://github.com/ergut/mcp-bigquery-server
cd mcp-bigquery-server
npm install
# Build
npm run build
Then update your Claude Desktop config to point to your local build:
{
"mcpServers": {
"bigquery": {
"command": "node",
"args": [
"/path/to/your/clone/mcp-bigquery-server/dist/index.js",
"--project-id",
"your-project-id",
"--location",
"us-central1",
"--key-file",
"/path/to/service-account-key.json"
]
}
}
}
MIT License - See LICENSE file for details.
Salih Ergรผt
This project is proudly sponsored by:
See CHANGELOG.md for updates and version history.
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by mckinsey
Build high-quality data visualization apps quickly with lowโcode configuration, leveraging Plotly, Dash, and Pydantic while allowing deep customisation through Python, JavaScript, HTML, and CSS.
by antvis
mcp-server-chart is a Model Context Protocol (MCP) server developed by AntV that generates over 25 types of visual charts. It provides robust chart generation and data analysis capabilities, integrating with various AI clients and platforms.
by reading-plus-ai
mcp-server-data-exploration is an MCP server designed for autonomous data exploration on CSV-based datasets. It acts as a personal Data Scientist assistant, providing intelligent insights with minimal effort.
by Canner
Wren Engine is a semantic engine designed for Model Context Protocol (MCP) clients and AI agents, enabling accurate and context-aware access to enterprise data.
by GongRzhe
A Model Context Protocol (MCP) server for generating various types of charts using QuickChart.io, enabling chart creation through MCP tools.
by isaacwasserman
Provides tools for saving data tables and generating VegaโLite visualizations via an MCP interface, supporting both textual specifications and PNG image output.
by surendranb
Google Analytics MCP Server is a Python-based tool that enables Large Language Models (LLMs) to access and analyze Google Analytics 4 (GA4) data using natural language, providing conversational querying of over 200 GA4 dimensions and metrics.
by tinybirdco
Provides a Model Context Protocol server implementation for Tinybird, allowing analytics agents to forward data to Tinybird's platform.
by GongRzhe
JSON-MCP-Server is a JSON Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to query and manipulate JSON data. It provides advanced data interaction capabilities through standardized tools and JSONPath syntax.