BigQuery

Provides access to BigQuery data to inspect schemas and execute SQL queries via MCP clients.

other

0

GitHub Stars

other

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

This BigQuery MCP Server lets you inspect BigQuery database schemas and execute SQL queries from an MCP client. It exposes tools to run queries, list tables, and describe table schemas, enabling you to build dynamic, data-informed interactions with BigQuery through the Model Context Protocol ecosystem.

How to use

You interact with the BigQuery MCP Server from an MCP client by calling its tools to inspect schemas and run queries.

How to install

Prerequisites: ensure you have the MCP runtime tooling installed and available in your environment. You will use the MCP runtime to start the server with the BigQuery configuration.

If you are using the published server configuration, start the server with the following command and replace the placeholders with your values:

uvx mcp-server-bigquery --project YOUR_GCP_PROJECT_ID --location YOUR_GCP_LOCATION

If you are developing locally and testing from source, you can start the server using the development command shown here. Replace PATH_TO_REPO with the path to your local repository and fill in your project and location values:

uv --directory PATH_TO_REPO run mcp-server-bigquery --project YOUR_GCP_PROJECT_ID --location YOUR_GCP_LOCATION

Additional content

Configuration details for the server are provided by the following arguments. You must supply the project and location. Optionally, you can limit the server to specific datasets by repeating the dataset flag.

--project (required): The GCP project ID.
--location (required): The GCP location (for example, europe-west9).
--dataset (optional): Only take specific BigQuery datasets into consideration. You can specify multiple datasets by repeating the argument (for example, --dataset my_dataset_1 --dataset my_dataset_2). If you omit this, all datasets in the project are considered.

Tools and capabilities

This server provides three tools to interact with BigQuery data from an MCP client:

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.

Available tools

execute-query

Executes a SQL query against BigQuery using the BigQuery dialect and returns the results to the MCP client.

list-tables

Retrieves a list of all tables accessible in the configured BigQuery datasets.

describe-table

Returns the schema details for a specific BigQuery table, including column names, types, and modes.