MarcoPolo
**MarcoPolo provides an easy, secure workspace for your data across 50+ systems.** MarcoPolo spins up a secure container where Cursor can work with your actual data. Connect to your databases, APIs, S3, lakehouses, CRMs, Jira, logs and much more—using scoped credentials that are never exposed to the model. Cursor gets DuckDB, Python, a shell, and a set of tools to explore, query, transform, and analyze data across systems. The workspace persists over time, so that you can build on your work. Prep a report, understand your data, debug an issue, or review the latest metrics right here in the conversation. 1. Explore and comprehend available data sources: - "Summarize schema and tables in Snowflake using an ER diagram" - "Generate a profile of the daily_metrics dataset in the AWS S3 bucket" 1. Gain actionable insights across multiple sources: - "Visualize product revenue from BigQuery for closed-won opportunities in 2025 in Salesforce" 1. Build and run data pipelines: - "Use Python to clean and transform the accounts data: standardize phone numbers and geocode addresses" 1. Validate and report on data quality: - "Run data quality checks: validate email formats, flag duplicates, check for nulls in required fields" 1. Triage and break fix: - "Dig through Prefect logs and figure out why nightly aggregation pipeline has been failing since Monday" <img width="2048" height="2048" alt="Image" src="https://github.com/user-attachments/assets/8183fbf9-10ec-4485-b0a5-5c98b545a8bb" />
MarcoPolo
**MarcoPolo provides an easy, secure workspace for your data across 50+ systems.** MarcoPolo spins up a secure container where Cursor can work with your actual data. Connect to your databases, APIs, S3, lakehouses, CRMs, Jira, logs and much more—using scoped credentials that are never exposed to the model. Cursor gets DuckDB, Python, a shell, and a set of tools to explore, query, transform, and analyze data across systems. The workspace persists over time, so that you can build on your work. Prep a report, understand your data, debug an issue, or review the latest metrics right here in the conversation. 1. Explore and comprehend available data sources: - "Summarize schema and tables in Snowflake using an ER diagram" - "Generate a profile of the daily_metrics dataset in the AWS S3 bucket" 1. Gain actionable insights across multiple sources: - "Visualize product revenue from BigQuery for closed-won opportunities in 2025 in Salesforce" 1. Build and run data pipelines: - "Use Python to clean and transform the accounts data: standardize phone numbers and geocode addresses" 1. Validate and report on data quality: - "Run data quality checks: validate email formats, flag duplicates, check for nulls in required fields" 1. Triage and break fix: - "Dig through Prefect logs and figure out why nightly aggregation pipeline has been failing since Monday" <img width="2048" height="2048" alt="Image" src="https://github.com/user-attachments/assets/8183fbf9-10ec-4485-b0a5-5c98b545a8bb" />