BigQuery Bikeshare

An example MCP Server to connect a LLM to BigQuery and other databases

python

2

GitHub Stars

python

Language

6 months ago

First Indexed

2 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": {
    "mohrstade-ap-training-bigquery-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/ap-training-bigquery-mcp",
        "run",
        "mcp_layer.py"
      ]
    }
  }
}

This MCP server provides a semantic layer for querying BigQuery’s Austin Bikeshare public dataset. It defines structured dimensions (trip_id, subscriber_type, bike_id, bike_type, station names) and measures (total_trip_count, trip_duration) to simplify data analysis through a clear, typed interface.

How to use

Connect an MCP client to the bigquery_bikeshare server to run analytical queries against the Bikeshare dataset. You will leverage the pre-defined semantic layer that exposes the core dimensions and measures, enabling you to compose queries that are easy to understand and fast to execute.

To enable this MCP server, you need the runtime configuration that points your client to the local MCP runner. Use the following configuration in your client setup to load the server from your MCP directory. The snippet assumes you extracted the MCP source to a local path on your machine.

{
  "mcpServers": {
    "bigquery_bikeshare": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/ap-training-bigquery-mcp",
        "run",
        "mcp_layer.py"
      ]
    }
  }
}

Available tools

define_dimensions

Creates structured dimensions such as trip_id, subscriber_type, bike_id, bike_type, and station names to organize data context.

define_measures

Establishes numeric measures like total_trip_count and trip_duration to quantify Bikeshare activity.

semantic_query_interface

Provides a simplified querying interface to retrieve analytics from the semantic layer without needing low-level SQL details.