BigQuery
(by LucasHild) - This server enables LLMs to inspect database schemas and execute queries on BigQuery.
What is BigQuery?
BigQuery is a Model Context Protocol server developed by LucasHild that facilitates large language models (LLMs) in inspecting database schemas and executing queries on Google BigQuery.
How to use BigQuery?
To use BigQuery, users must configure the server with the Google Cloud Project ID and location, then execute queries through the provided tools. Users can list tables, describe table schemas, and run SQL queries.
Key features of BigQuery?
- Execute SQL queries using BigQuery dialect
- List all tables in a BigQuery database
- Describe the schema of specific tables
Use cases of BigQuery?
- Integrating LLM capabilities for seamless database querying.
- Assisting data analysts in managing large datasets by allowing natural language queries.
- Enhancing application features requiring real-time database schema inspection and querying capabilities.
FAQ from BigQuery?
- What is required to run BigQuery?
You need a valid Google Cloud Project ID and specify a location in the configuration.
- Can I query different datasets within the same project?
Yes, you can specify multiple datasets during configuration.
- Is it necessary to install dependencies before using the server?
Yes, dependencies need to be synced and the package built before execution.
# 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 with the following arguments:
- `--project` (required): The GCP project ID.
- `--location` (required): The GCP location (e.g. `europe-west9`).
- `--dataset` (optional): 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`). If not provided, all tables in the project will be considered.
Quickstart
Install
Claude Desktop
On MacOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json` On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
<details> <summary>Development/Unpublished Servers Configuration</summary> ``` "mcpServers": { "bigquery": { "command": "uv", "args": [ "--directory", "{{PATH_TO_REPO}}", "run", "mcp-server-bigquery", "--project", "{{GCP_PROJECT_ID}}", "--location", "{{GCP_LOCATION}}" ] } } ``` </details>
<details> <summary>Published Servers Configuration</summary> ``` "mcpServers": { "bigquery": { "command": "uvx", "args": [ "mcp-server-bigquery", "--project", "{{GCP_PROJECT_ID}}", "--location", "{{GCP_LOCATION}}" ] } } ``` </details>
Replace `{{PATH_TO_REPO}}`, `{{GCP_PROJECT_ID}}`, and `{{GCP_LOCATION}}` with the appropriate values.
Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
```bash uv sync ```
- Build package distributions:
```bash uv build ```
This will create source and wheel distributions in the `dist/` directory.
- Publish to PyPI:
```bash 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](https://github.com/modelcontextprotocol/inspector).
You can launch the MCP Inspector via [`npm`](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) with this command:
```bash 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.
