LABSCO SUMMARY

Schema first, then the query - the loop that usually costs two failed attempts.

It lists tables and describes them before anything runs, so column names get copied rather than guessed. Restricting it to named datasets happens at launch, which means the reach of the query tool is decided before the model ever sees it.

What it is

Three tools over a BigQuery project: the tables it can see, the schema of one of them, and a query in BigQuery dialect.

What you get

Every table in the project, or only in the datasets you name
The schema of a specific table
A SQL query executed in BigQuery dialect, with rows returned inline

Requirements

A GCP project and its location - both required, given either as launch arguments or as environment variables. An optional dataset setting narrows the server to named datasets, and several can be listed.

Setup effort

Add the configuration to your client

See installation options

USE CASES

01

Getting oriented in a project you did not build

List what tables exist, then read the schema of the ones that sound relevant, before writing a line of SQL.

list-tablesdescribe-table

02

Answering a data question where it was asked

Run the query in the conversation and get the rows back inline, rather than switching to the console and pasting the result.

execute-query

03

Writing a query against a table you have never read

Read the schema first so column names and types are copied rather than guessed, then run it.

describe-tableexecute-query

3 tools

Listed in project docs. Your client may show a different list.

execute-query

list-tables

describe-table

BEFORE YOU INSTALL

What to know first

Tools you get

3 tools named in the project's documentation.

Requires

uvx on PATH
A Google Cloud project with BigQuery: BIGQUERY_PROJECT and BIGQUERY_LOCATION (or --project and --location)

Where it runs

All 3 documented clients run the server on your machine.

INSTALLATION

Connect your client

MCP Clients

Claude Code

CLAUDE CODE · TERMINAL

claude mcp add bigquery --scope user --transport stdio -- uvx mcp-server-bigquery --project <YOUR_BIGQUERY_PROJECT> --location <YOUR_BIGQUERY_LOCATION>

<YOUR_BIGQUERY_PROJECT> is your GCP project ID, and <YOUR_BIGQUERY_LOCATION> is your BigQuery location (for example europe-west9), braces included. The server uses your machine's default Google Cloud credentials unless you give it a service-account key file.

Claude Desktop, Cursor

JSON

{
  "mcpServers": {
    "bigquery": {
      "command": "uvx",
      "args": [
        "mcp-server-bigquery"
      ],
      "env": {
        "BIGQUERY_PROJECT": "<YOUR_BIGQUERY_PROJECT>",
        "BIGQUERY_LOCATION": "<YOUR_BIGQUERY_LOCATION>"
      }
    }
  }
}