BigQuery MCP Server
Provides tools for executing SQL queries, listing datasets and tables, getting table schemas, previewing table data, and retrieving table metadata in Google BigQuery.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@BigQuery MCP Serverlist tables in the analytics dataset"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BigQuery MCP Server
A custom MCP server for Google BigQuery with service account authentication.
Setup
Install dependencies:
pip install -r requirements.txtSet environment variables:
export BQ_SERVICE_ACCOUNT_KEY="/path/to/your-service-account-key.json" export BQ_PROJECT_ID="your-default-project-id"Run the server:
python bigquery_mcp.py
Related MCP server: BigQuery MCP Server
Configuration for Claude Desktop / Cowork
Add this to your MCP settings (e.g. claude_desktop_config.json):
{
"mcpServers": {
"bigquery": {
"command": "python",
"args": ["/path/to/bigquery_mcp.py"],
"env": {
"BQ_SERVICE_ACCOUNT_KEY": "/path/to/your-service-account-key.json",
"BQ_PROJECT_ID": "looplink-drt"
}
}
}
}Available Tools
Tool | Description |
| Run a read-only SQL query |
| List all datasets in a project |
| List tables in a dataset |
| Get column definitions for a table |
| Preview first N rows (free, no query cost) |
| Get table metadata (rows, size, partitioning) |
Notes
Only SELECT queries are allowed (safety enforced)
10 GB billing cap per query
Supports both
looplink-drtanddandelion-tf-productionprojects viaproject_idparameter
This server cannot be deployed
Maintenance
Related MCP Connectors
Provides read access to your GKE and Kubernetes resources.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
The BigQuery remote MCP server is a fully managed service that uses the Model Context Protocol to connect AI applications and LLMs to BigQuery data sources. It provides secure, standardized tools for AI agents to list datasets and tables, retrieve schemas, generate and execute SQL queries through natural language, and analyze data—enabling direct access to enterprise analytics data without requiring manual SQL coding.
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables reading BigQuery data from ChatGPT using read-only SQL queries, with OAuth authentication and project-level access control.-
- AlicenseNot gradedqualityCmaintenanceEnables LLMs to explore BigQuery datasets and tables, run safe read-only queries, and optionally perform vector search using BigQuery embeddings.80 PyPI10MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to query and analyze Google BigQuery data, including schema browsing, running queries, and comparing datasets through natural language.MIT
- FlicenseNot gradedqualityCmaintenanceEnables running read-only SQL queries and exploring DuckDB databases through MCP tools like listing tables, describing schemas, and fetching paginated data.-