Skip to main content

Agents

There are three complementary ways to use AI agents with Bauplan. They are not mutually exclusive and can be combined depending on the workflow.

To get started, follow the skills setup guide.

1. MCP server​

The Bauplan MCP Server is a Model Context Protocol integration that gives AI assistants direct access to your Bauplan data lakehouse. Instead of guessing at API syntax or table structures, the assistant gets real-time context, improving code quality and reducing hallucinations in generated SQL and Python.

Through the MCP server, an assistant can:

  • Inspect schemas and tables
  • Run queries
  • Manage data branches and commits
  • Run Bauplan projects and pipelines
  • Track and inspect jobs

The MCP server is primarily intended for connection to non-technical tools such as Claude Desktop or the ChatGPT app, where an assistant needs live access to lakehouse state. For setup instructions, configuration examples, and usage videos, visit the repository.

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

2. Repository-based usage (CLAUDE.md + CLI / SDK)​

Bauplan can also be used with LLMs without running an MCP server.

In this mode, the assistant operates purely through repository context:

  • A CLAUDE.md file at the project root that explains how to work with Bauplan
  • Reference documentation for the Bauplan CLI and Python SDK
  • Standard command-line execution and code generation

The assistant reads documentation, writes Python or SQL, and invokes Bauplan through the CLI or SDK directly. Functionally, this covers the same core operations as the MCP server, but without requiring a long-running service.

This approach is well suited to IDE-based assistants like Claude Code or Cursor and is often the simplest starting point.

See: https://github.com/BauplanLabs/bauplan-skills/blob/main/CLAUDE.md

3. Agent Skills for structured workflows​

Agent Skills are reusable, declarative workflow templates designed to guide LLMs through multi-step data engineering tasks. Skills are distributed as a Claude Code plugin that installs and updates automatically; see the skills setup guide.

Skills encode best practices and sequencing for tasks that are otherwise easy to get wrong, including:

  • Creating new data pipelines
  • Ingesting data safely using Write-Audit-Publish
  • Exploring large or complex datasets
  • Investigating failed runs and performing root-cause analysis

Each skill defines the intent, constraints, and expected steps of a workflow, while still operating on the same underlying Bauplan primitives (branches, runs, validation, publish). Skills can be used together with the MCP server or with repository-based usage.

See: https://github.com/BauplanLabs/bauplan-skills