MCP Server & Skills

The MCP Server is a Model Context Protocol integration that gives AI assistants direct access to your Bauplan data lakehouse. Instead of just reading documentation, your AI coding partner can query tables, inspect schemas, run pipelines, and manage branches directly.

Repository: https://github.com/BauplanLabs/bauplan-mcp-server

What it does

The MCP server exposes lakehouse operations through the Model Context Protocol, enabling AI assistants (Claude Code, Claude Desktop, Cursor) to interact with Bauplan via tool calls. This provides real-time context about your lakehouse state, improving code quality and reducing hallucinations in generated SQL and Python.

Rather than requiring the assistant to guess at API syntax or table structures, the server gives them accurate, up-to-date information about your data landscape.

Available Skills

The MCP server includes four reusable skill definitions for common workflows:

1. New Pipeline (new-pipeline)

Create a new Bauplan data pipeline project from scratch, including SQL and Python models. This skill guides the assistant through proper project setup, model definitions, and initial validation.

2. Write-Audit-Publish (wap)

Implements the Write-Audit-Publish pattern to safely ingest data from S3 with quality checks before production release. This ensures data quality gates are enforced before publishing to main.

3. Explore Data (explore-data)

Provides structured investigation of the Bauplan lakehouse through schema inspection, data sampling, and query generation. Use this when you need to understand unfamiliar datasets or validate data assumptions.

4. Root Cause Analysis (root-cause-analysis)

Enables diagnosis and resolution of data issues within the lakehouse ecosystem. This skill helps trace failures back to their source and suggests remediation steps.

Getting Started

For setup instructions, configuration examples, and usage videos, visit the GitHub repository.