MCP server
BigQuery MCP server
Google's remote BigQuery MCP server lets AI list datasets and tables and run SQL, with a read-only query tool and IAM controls.
- Official server
- Databases
At a glance
- Maintained by
- Google Cloud
- Tools exposed
- 6 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
BigQuery is Google Cloud's data warehouse, often home to analytics exports, marketing data and business reporting. Google hosts an official remote MCP server for it. An assistant can list datasets and tables, read table details and run SQL, with Google Cloud identity and IAM roles deciding what it can see.
For teams that already send Google Analytics or ad data to BigQuery, this is a direct path from question to answer.
The server offers a read-only query tool and a full SQL tool. We use the read-only tool for business users and block the full tool with an IAM deny policy where writes are not needed. Keep an eye on query costs, since large scans are billed.
Use cases
Best business use cases
Marketing analysis
Dataset discovery
Report drafts
Ad hoc questions
Analytics agents
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read by default with execute_sql_readonly; execute_sql allows writes and can be blocked with an IAM deny policy.
-
list_dataset_idsLists datasets in a project.
-
get_dataset_infoGets dataset metadata.
-
list_table_idsLists tables in a dataset.
-
get_table_infoGets table schema and metadata.
-
execute_sql_readonlyRuns read-only SQL queries.
-
execute_sqlRuns read-write SQL; 3 minute timeout, 3,000 row limit.
Workflows
Example workflows
Campaign performance question
-
1
Grant the assistant a role with data viewer access.
-
2
Ask for conversions by campaign last month.
-
3
It finds the right table and writes SQL.
-
4
It runs the read-only query.
-
5
It summarizes results and flags outliers.
Onboard a new analyst
-
1
The analyst asks what datasets exist.
-
2
The assistant lists them with descriptions.
-
3
It describes key tables and fields.
-
4
It runs a sample query.
-
5
The analyst builds on the example.
Prompts
Example prompts
“Which campaigns had the most conversions last month, and at what cost per conversion?”
“List our datasets and describe the main tables in each.”
“Estimate how much data this query would scan before running it.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"name": "bigquery",
"url": "https://bigquery.googleapis.com/mcp",
"type": "streamable-http"
}Claude Code: terminal
claude mcp add --transport http bigquery https://bigquery.googleapis.com/mcp- Hosted server: https://bigquery.googleapis.com/mcp (Streamable HTTP, Google OAuth 2.0 and IAM).
- Needs: Google Cloud identity via OAuth 2.0 (scope https://www.googleapis.com/auth/bigquery); IAM roles: roles/mcp.toolUser, roles/bigquery.jobUser, roles/bigquery.dataViewer; BigQuery API enabled in the project.
Security
Security considerations
-
Read-only tool
Prefer the read-only SQL tool and block full SQL with IAM where possible.
-
IAM roles
Grant only the roles the task needs.
-
Cost control
Large queries are billed. Set quotas and review scans.
-
Sensitive data
Use authorized views to hide personal data.
Related servers
Servers that pair well with it
Snowflake
Snowflake's managed MCP server exposes admin-defined tools, such as Cortex agents, Cortex Analyst, Cortex Search and SQL, to AI assistants.
Google Analytics
Google Analytics' official MCP server lets AI run GA4 reports, funnels and realtime reports and read property settings. Read-only.
Google Cloud
Google's gcloud MCP servers let AI run gcloud commands, read logs, metrics, alerts and traces, and work with Cloud Storage.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- Database design Data models that stay fast and correct as your business grows, with backups and access rules in place.
- Multi-tenant architecture One product serving many customer accounts, with each account's data kept separate and secure.
- Product scaling Keep a growing product fast and stable as users, data and features increase.
- Web applications Custom browser-based software for the work your team does every day, from booking tools to operations systems.
- Dashboards and reporting Dashboards that pull numbers from the systems you already use and show what matters without a spreadsheet.
Solutions
View all solutions- Automated reporting Reports that build themselves from your systems on schedule, with a plain-language summary of what changed.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- Forecasting dashboards Forecast demand from your sales history and seasonality, and flag items to reorder before they run out.
- Payroll automation Turn pay rules, attendance and leave into tested software so the monthly run becomes a review and payslips go out in one batch.
Industries
View all industries- Retail Stock forecasting, sales dashboards, feedback analysis and store tools for retailers with shops and online sales.
- Manufacturing Quality inspection, production dashboards, quoting tools, knowledge assistants and legacy system modernization for manufacturers.
- Marketing agencies Landing pages, content workflows, client reporting and white-label development capacity for marketing agencies.
Case studies
View all case studiesGuides and articles
View all guides and articles- How to connect AI to your database safely Let staff ask questions of your data in plain English without risking production systems or sensitive records.
- PostgreSQL vs MySQL The two most popular open-source databases compared for business applications.
- How to automate reporting with AI and MCP Build reports that assemble themselves from your systems through MCP, with a written summary people can trust.
- How to set up automated reporting Replace manual weekly and monthly reports with dashboards and summaries that update themselves.
AI models
View all ai models- text-embedding-3-large OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
- text-embedding-3-small OpenAI's efficient, lowest-cost embedding model, with 1,536-dimension vectors for search, retrieval and similarity at scale.
- Cohere Embed v4 Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
- Voyage 4 Voyage AI's current embedding series, now part of MongoDB, with large, standard and lite models that share one embedding space.
- Embeddings Models that turn text into vectors for search, retrieval, clustering and recommendations.
- Gemma 4 Google's open-weight model family under Apache 2.0, in sizes from phone-friendly to 31B, with image input and function calling.
Glossary terms
View all glossary terms- Database A database is an organized store of data that software can search, update and keep consistent, such as customers, orders or bookings.
- Machine learning Machine learning is a way of building software that learns patterns from data to make predictions or decisions, instead of following only hand-written rules.
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
- Backend The backend is the part of an application that runs on servers, storing data, applying business rules and serving the frontend through APIs.
- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is hosted by Google Cloud.
It has a read-only query tool and a full SQL tool. Block the full tool with IAM if you do not need writes.
Queries are billed as normal BigQuery usage. Set quotas and review large queries.