BigQuery MCP Server

What is BigQuery MCP Server about?

Enables language models to list tables, describe table schemas, and run SQL queries against a Google BigQuery project using a standardized MCP tool interface.

How to use BigQuery MCP Server?

1. Install – either via the Smithery CLI (npx -y @smithery/cli install mcp-server-bigquery --client claude) or by cloning the repository and using Python's uv.
2. Configure – supply the GCP project ID and location (required) and optionally datasets or a service‑account key file via command‑line flags or environment variables (BIGQUERY_PROJECT, BIGQUERY_LOCATION, BIGQUERY_DATASETS, BIGQUERY_KEY_FILE).
3. Run – start the MCP server (e.g., uv run mcp-server-bigquery --project <PROJECT_ID> --location <LOCATION>). The server communicates over stdio, allowing Claude Desktop or any MCP‑compatible client to invoke the tools.

Key Features

• execute‑query: Runs arbitrary SQL in BigQuery dialect and returns results.
• list‑tables: Retrieves a list of all tables across the configured datasets.
• describe‑table: Returns the schema of a specific table, including column names and types.
• Supports multiple datasets and custom service‑account credentials.
• Fully container‑izable and publishable to PyPI for easy distribution.

Use Cases

• Data exploration: Let an LLM explore the structure of a BigQuery warehouse without manual SQL writing.
• Automated reporting: Generate dynamic reports by having the model construct and execute queries on‑the‑fly.
• Chat‑based analytics: Integrate with Claude Desktop or other LLM UIs to answer business questions directly from the data lake.
• Development debugging: Use the MCP Inspector to step through tool calls and view raw queries/results.

FAQ

• Do I need a service‑account key? Only if the default Google credentials on the host are insufficient. Provide the path via --key-file or BIGQUERY_KEY_FILE.
• Can I limit the server to specific datasets? Yes, use the --dataset flag multiple times or set BIGQUERY_DATASETS as a comma‑separated list.
• What runtime is required? Python 3.9+ and the uv package manager (or any compatible environment that can run the entry‑point mcp-server-bigquery).
• How do I debug tool calls? Launch the MCP Inspector with npx @modelcontextprotocol/inspector uv --directory <repo> run mcp-server-bigquery and follow the generated URL.
• Is the server published to PyPI? Yes, after building with uv build you can publish using uv publish.

BigQuery MCP server

A Model Context Protocol server that provides access to BigQuery. This server enables LLMs to inspect database schemas and execute queries.

Components

Tools

The server implements one tool:

• execute-query: Executes a SQL query using BigQuery dialect
• list-tables: Lists all tables in the BigQuery database
• describe-table: Describes the schema of a specific table

Configuration

The server can be configured either with command line arguments or environment variables.

Argument	Environment Variable	Required	Description
--project	BIGQUERY_PROJECT	Yes	The GCP project ID.
--location	BIGQUERY_LOCATION	Yes	The GCP location (e.g. europe-west9).
--dataset	BIGQUERY_DATASETS	No	Only take specific BigQuery datasets into consideration. Several datasets can be specified by repeating the argument (e.g. --dataset my_dataset_1 --dataset my_dataset_2) or by joining them with a comma in the environment variable (e.g. BIGQUERY_DATASETS=my_dataset_1,my_dataset_2). If not provided, all datasets in the project will be considered.
--key-file	BIGQUERY_KEY_FILE	No	Path to a service account key file for BigQuery. If not provided, the server will use the default credentials.

Quickstart

Install

Installing via Smithery

To install BigQuery Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install mcp-server-bigquery --client claude

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration

"mcpServers": {
  "bigquery": {
    "command": "uv",
    "args": [
      "--directory",
      "{{PATH_TO_REPO}}",
      "run",
      "mcp-server-bigquery",
      "--project",
      "{{GCP_PROJECT_ID}}",
      "--location",
      "{{GCP_LOCATION}}"
    ]
  }
}

Published Servers Configuration

"mcpServers": {
  "bigquery": {
    "command": "uvx",
    "args": [
      "mcp-server-bigquery",
      "--project",
      "{{GCP_PROJECT_ID}}",
      "--location",
      "{{GCP_LOCATION}}"
    ]
  }
}

Replace {{PATH_TO_REPO}}, {{GCP_PROJECT_ID}}, and {{GCP_LOCATION}} with the appropriate values.

Development

Building and Publishing

To prepare the package for distribution:

1. Increase the version number in pyproject.toml

2. Sync dependencies and update lockfile:

uv sync

3. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

4. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory {{PATH_TO_REPO}} run mcp-server-bigquery

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.