takuya0206_bigquery-mcp-server

takuya0206_bigquery-mcp-server

3.1

If you are the rightful owner of takuya0206_bigquery-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A Model Context Protocol (MCP) server for accessing Google BigQuery, enabling Large Language Models (LLMs) to understand dataset structures and execute SQL queries.

The BigQuery MCP Server is designed to facilitate seamless interaction between Large Language Models (LLMs) and Google BigQuery. By leveraging the Model Context Protocol, this server allows LLMs to comprehend the structure of BigQuery datasets and execute SQL queries efficiently. It supports robust authentication mechanisms, including Application Default Credentials and service account key files, ensuring secure access to BigQuery resources. The server is equipped with various tools to perform read-only operations, such as querying datasets, listing datasets and tables, and retrieving table information. It also includes features for query validation and cost estimation, making it a comprehensive solution for managing BigQuery interactions. With a focus on security, the server enforces read-only access and provides recommendations for optimizing query performance, particularly for partitioned tables.

Features

  • Authentication and Connection Management: Supports ADC and service account key files with configurable project ID and location settings.
  • Query Execution: Allows execution of read-only SQL queries with configurable result limits and security checks.
  • Dataset and Table Management: Tools to list datasets and tables, including schema and partitioning information.
  • Query Validation: Dry-run feature to check query validity and estimate costs without execution.
  • Security Features: Enforces read-only access and provides partition filter recommendations.

Tools

  1. query

    Execute read-only (SELECT) BigQuery SQL queries.

  2. list_all_datasets

    List all datasets in the project.

  3. list_all_tables_with_dataset

    List all tables in a specific dataset with their schemas.

  4. get_table_information

    Get table schema and sample data.

  5. dry_run_query

    Check query validity and estimate cost without execution.