Google BigQuery MCP Server

Connect your account, then chat with AI to run tools.

Google BigQuery is a serverless, highly scalable data warehouse with built-in machine learning capabilities. Run SQL queries on massive datasets, perform real-time analytics, integrate machine learning models, and analyze petabytes of data with automatic scaling and optimization for business intelligence and data science.

Start chatting

Managed

10 tools

Agent guide included

Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.

Browse all tools

AI Skill
SKILL.md

Domain knowledge for Google BigQuery — workflow patterns, data models, and gotchas for your AI agent.

BigQuery

BigQuery uses project/dataset/table hierarchy. Run SQL, list datasets/tables, preview rows. Auth via service account JSON.

Data Model

Datasets contain tables. Format: project.dataset. List datasets for discovery.
Tables are in datasets. List tables by dataset_id. Get schema, preview, stats, list rows.
Search runs parameterized SQL. Returns rows with resource ids for fetch (bigquery:row:...).
Queries: Standard SQL. Fully qualified names: project.dataset.table.

Gotchas

Fully qualified names: Use backticks for project.dataset.table when project has hyphens/dots.
Service account: Auth via JSON key. Uses Google SDK, not HTTP headers.
Resource id: From search results for fetch. Format includes project, dataset, table, row identifier.

Tools in this Server (10)

Bigquery Execute

Execute write operations on BigQuery (INSERT, UPDATE, DELETE, DDL). Changes are permanent.

Bigquery Get AI Description

Get compact, AI-friendly description of BigQuery project structure.

Bigquery Get Table Schema

Get detailed schema for a BigQuery table.

Bigquery Get Table Stats

Get statistics for a BigQuery table including row count and size.

Bigquery List Datasets

List all datasets in a BigQuery project.

Bigquery List Rows

List rows from a BigQuery table with filtering and pagination.

Bigquery List Tables

List tables in a BigQuery dataset.

Bigquery Preview Table

Preview first N rows from a BigQuery table.

Fetch

Fetch BigQuery table metadata by ID.

Execute SQL queries on BigQuery. Returns query results with column names and values. Maximum 1000 rows.

Frequently Asked Questions

What is the Google BigQuery MCP server?

How do I connect Google BigQuery to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/bigquery. Authentication is handled automatically.

How many tools does Google BigQuery provide?

Google BigQuery provides 10 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Google BigQuery require?

Google BigQuery uses API Key. Google BigQuery requires credentials. Connect via MCPBundles and authentication is handled automatically.

Setup Instructions

Connect Google BigQuery to any MCP client in minutes

MCP URL

https://mcp.mcpbundles.com/bundle/bigquery

Claude.ai Cursor VS Code VS Code Insiders Goose LM Studio Cherry Studio ChatGPT

One-click install:

Install on Claude.ai Install for organization (admins)

The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.

Or add manually

Open claude.ai → Settings → Connectors.
Click the + button and choose Add custom connector.
Set Name to Google BigQuery and paste the MCP URL into Remote MCP server URL.
Click Add. Google BigQuery will appear under Not connected — select it and click Connect to complete OAuth.