AI Plugin IndexStarter stack
The AI plugin stack for data engineers
Warehouses, pipelines and transformation tools your assistant can query and debug.
Warehouses
Query and inspect tables without switching tools.
OpenTabs plugin for Snowflake — run SQL queries, browse database schemas, and manage worksheets
Generate CocoMeter chargeback invoices. Usage: $meter invoice
MCP server for Google BigQuery, built for the Analytics Model platform connector contract
MCP server for interacting with BigQuery databases
Pipelines and modelling
Check DAG runs and dbt models.
Airflow adapter pattern for v2/v3 API compatibility. Use when working with adapters, version detection, or adding new API methods that need to work across Airflow 2.x and 3.x.
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.
Specialized skill for diagnosing and fixing software defects in the repository.
Connect an AI coding agent to Snowflake, BigQuery, Databricks, or ClickHouse so it can run SQL. Use when warehouse access is missing, authentication or connection selection is required, or before using a warehouse-data skill such as agents-schema-search.
Local analytics
Fast analysis on files and small datasets.
Native Node.js/TypeScript implementation of DuckDB MCP extension
Load when hitting DuckDB syntax errors or writing DuckDB-specific SQL. Covers gotchas that differ from PostgreSQL/MySQL.
MCP server (stdio) for AI agents to safely read, edit and run local Jupyter notebooks — zero service, CAS-guarded edits, resumable execution.
MCP server for live JupyterLab notebooks over RTC: read, edit and run cells in the document the user is looking at.