googlebigquery-automation

Automate Google BigQuery tasks via Rube MCP (Composio): run SQL queries, explore datasets and metadata, execute MBQL queries via Metabase integration. Always search tools first for current schemas.

Install

Hot:16

Download and extract to your skills directory

Copy command and send to OpenClaw for auto-install:

Download and install this skill https://openskills.cc/api/download?slug=composiohq-composio-skills-googlebigquery-automation&locale=en&source=copy

Google BigQuery Automation via Rube MCP

Skills Overview


By integrating Rube MCP (Composio) with Metabase, automate the execution of Google BigQuery queries, explore dataset schemas, and retrieve metadata. Supports two query modes: native SQL and MBQL.

Use Cases

  • Automated Enterprise Data Analysis

  • Connect BigQuery through Metabase to automatically run scheduled report queries, perform data aggregation, and analyze trends, reducing manual work and repetitive tasks.

  • Data Warehouse Architecture Exploration

  • Quickly retrieve BigQuery database table structures, field information, and metadata to help data engineers and analysts understand the data warehouse architecture without writing additional code.

  • BI Tool Integrated Querying

  • Use Metabase as an intermediary layer to interact with BigQuery via MBQL or native SQL. Suitable for scenarios where query capabilities need to be integrated into custom applications or workflows.

    Core Features

  • Native SQL Query Execution

  • Use the METABASE_POST_API_DATASET tool to directly run standard BigQuery SQL statements. Supports parameterized queries and control over result set size, making it ideal for complex analysis and custom data processing.

  • MBQL Structured Query

  • Execute structured queries with built-in aggregations, filters, and sorting via Metabase Query Language, which are automatically converted into optimized SQL. Best for standardized report and dashboard data sources.

  • Metadata and Schema Exploration

  • Use METABASE_GET_API_DATABASE and related tools to quickly list available databases and retrieve complete table structure information, helping you understand the data schema before writing queries.

    Common Questions

    How to connect BigQuery through Rube MCP?


    Rube MCP connects to BigQuery through Metabase as an intermediary. First, add https://rube.app/mcp as the MCP server, then use the RUBE_MANAGE_CONNECTIONS tool and set the toolkit to metabase to complete authorization. After the connection is activated, the configured BigQuery data sources in Metabase can be used. Note: The BigQuery project must be configured as a data source in Metabase first.

    What is the difference between MBQL and native SQL?


    MBQL (Metabase Query Language) is a structured query language that builds queries using field IDs, aggregation types, and filtering conditions, and automatically converts them into optimized SQL. Native SQL directly writes standard BigQuery SQL, offering greater flexibility but requiring syntax familiarity. Recommendation: use MBQL for standardized reports, and native SQL for complex analysis. The two can be converted via the METABASE_POST_API_DATASET_NATIVE tool.

    How to get the BigQuery database ID?


    A database ID is an internal integer identifier in Metabase, not the BigQuery project name. Use the METABASE_GET_API_DATABASE tool to list all configured databases and their IDs. After obtaining the ID, you can use METABASE_GET_API_DATABASE_ID_METADATA to retrieve complete table and field metadata, ensuring your queries use the correct table and field identifiers.