Bigquery Mcp

io.github.SnowLeopard-AIPublished by GitHub account SnowLeopard-AIv0.1.1Updated Oct 24, 2026

A SnowLeopardAI-managed MCP server that provides access to Google BigQuery data.

VerifiedSTDIODesktop onlyDatabasesData & Analytics

Overview

AI-generated overview

Lets an assistant explore Google BigQuery datasets and run SQL queries against them through natural language.

What you can do
This MCP server bridges an AI assistant to Google BigQuery. It exposes resources that list available tables and return a table's schema, and tools for listing tables, fetching schemas, and executing BigQuery SQL with the query tool. Datasets and tables can be scoped at startup, and results come back from the query tool for the assistant to interpret.
When to use it
Use it when you want an assistant to answer questions about data already stored in BigQuery, explore table structures, or run ad hoc SQL without leaving the chat. It suits analysts and developers who already work with BigQuery projects and want conversational access to them.
Requirements
Runs locally as a Python package (sl-bigquery-mcp) launched via uvx, so Python tooling and the uv package manager are needed. It requires a Google Cloud project with BigQuery enabled and application default credentials obtained through gcloud auth application-default login. The project is passed with the --project option or the BQ_PROJECT environment variable, and datasets or tables are set with --dataset or --table. Desktop client only.
Before you install
The server runs BigQuery SQL on your behalf, so queries can read data and may incur BigQuery job and storage costs on the configured project. It relies on your Google Cloud application default credentials, which grant whatever access that account has. Review the dataset and project scope you configure, and be aware that query results are returned to the assistant and its model provider.

Installation

In SourceWeft

  1. Open Bigquery Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Snow Leopard BigQuery MCP

[Test] [Coverage] [PyPI - Version] [Discord]




A Model Context Protocol (MCP) server for Google BigQuery that enables AI agents to interact with BigQuery databases through natural language queries and schema exploration.

This project was developed by Snow Leopard AI as a benchmarking tool for our platform, and we're making it publicly available for the community to use and build upon.

What is MCP?

The Model Context Protocol (MCP) is an open standard that allows AI applications to securely connect to external data sources and tools. This BigQuery MCP server acts as a bridge between AI agents and your BigQuery datasets.

Snow Leopard BigQuery MCP Server Features

Resources

Resource URIDescription
bigquery://tablesList all tables available to the agent
bigquery://tables/{table}/schemaGet the schema of a specific table

Tools

ToolDescription
list_tables(table: str) (optional)List available tables
get_schema(table: str) (optional)Get the schema of a given table
query(sql: str)Execute BigQuery SQL and return results

Quick Start: Claude Desktop

Prerequisites

Before getting started, ensure you have:

1. Setup Google Cloud

First, we need to authenticate with Google.

bash
gcloud auth application-default login

This opens your browser to authenticate your local machine with Google Cloud.

2. Configure Claude Desktop

Edit your claude_desktop_config.json file to add the BigQuery MCP server.

Application: Claude > Settings > Developer > Edit Config
Mac: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\\Claude\\claude_desktop_config.json

You will need to set your project to a Google Cloud project with permissions to submit bigquery jobs. If you do not have a project that you can run bigquery jobs on, create and test one by following Google's BigQuery Quickstart Guide Create a project and follow the instructions to query a public dataset.

json
{  "mcpServers": {    "bigquery": {      "command": "uvx",      "args": [        "sl-bigquery-mcp",         "--dataset",        "bigquery-public-data.usa_names",        "--project",        "🚨 <projectName> 🚨"      ]    }  }}

3. Close Claude Desktop and Launch it from the terminal

Depending on how you have installed uv, the uvx executable may not be in Claude Desktop's PATH if it is launched from the GUI. To be sure uvx is accessible from Claude Desktop, let's run it in the terminal.

bash
open -a claude

After saving the configuration, restart Claude Desktop. You should now be able to ask Claude questions about your BigQuery data!

Example Query
What are the top 10 most popular names in 2020?

Configuration Options

To see a complete list of parameters:

bash
uvx sl-bigquery-mcp --help
Usage: sl-bigquery-mcp [OPTIONS]
╭─ Options ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮│ --mode                       [stdio|sse|streamable-http]  MCP transport protocol [default: stdio]                                                     ││ --dataset                    TEXT                         Dataset(s) for mcp resources. Will create resources for all tables.                         ││ --table                      TEXT                         Table(s) for mcp resources. Can be specified as project.dataset.table or dataset.table      ││ --enable-list-tables-tool    --no-enable-list-tables-tool Registers list_resources tool [default: enable-list-tables-tool]                            ││ --enable-schema-tool         --no-enable-schema-tool      Registers get_schema tool [default: enable-schema-tool]                                     ││ --project                    TEXT                         BigQuery project [env var: BQ_PROJECT] [default: None]                                      ││ --api-method                 [INSERT|QUERY]               BigQuery client api_method [default: QUERY]                                                 ││ --port                       INTEGER                      [default: 8000]                                                                             │╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Troubleshooting / FAQ

An MCP Error has occurred

First, check out your Claude Desktop app logs (in the same directory as the config file) for more verbose errors / logging

On Startup

This usually means Claude is having issues starting the mcp server. Frequently this is due to uvx being inaccessible from the application. In this case, use the full path to your uvx executable instead of just uvx in claude_desktop_config.json.

To find your uv executable, run

bash
which uvx

Otherwise, this may be caused by bad arguments, dependency version incompatibilities, or bugs. If you run into the last two, please file an issue describing the problem.

On Resource / Tool Usage

This may be a misconfiguration mcp server, authentication issues, the llm getting too much data, or of course, product bugs. After checking the logs, consider using the MCP Inspector to debug your issue. And of course, file any bugs you find on our issue board.

Local Development & Testing

Setup Development Environment

  1. Clone the repository
  2. Setup virtual environment and install dependencies
  3. Verify installation
bash
git clone https://github.com/SnowLeopard-AI/bigquery-mcp.gitcd bigquery-mcp
uv syncsource .venv/bin/activate
sl-bigquery-mcp --help

Authenticate with Google Cloud

The following command will launch a browser for you to login to your google cloud account. You must have a Google Cloud project with BigQuery enabled. If you don't, see Google's bigquery setup guide.

bash
gcloud auth application-default logingcloud config set project <projectName>gcloud auth application-default set-quota-project <projectName>

Running Tests

Run the tests to make sure your dev environment is properly configured.

bash
pytest tests

Note: the tests run actual BigQuery queries against public datasets and require authentication.

Local MCP Inspector

For hands-on testing and development, use the MCP Inspector tool:

bash
npx @modelcontextprotocol/inspector uv run sl-bigquery-mcp --dataset bigquery-public-data.usa_names

Contributing

We welcome contributions! Please coordinate with us on discord to ensure your changes can quicly make it into the repo. Communicating before coding always saves time.

For logistics of contributing to an open source project, see the first contributions repository.

Support

Issues: GitHub Issues
Documentation: BigQuery Documentation
MCP Protocol: Model Context Protocol
Contact: Discord Server

Source: README.md at commit d32a772

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts