LakeLogic MCP¶
Help AI assistants check and test data contracts locally.
Validate Open Lakehouse Contracts (OLC), find governance gaps, explain rules and generate sample data. Test-run contracts with LakeLogic Core using Polars or DuckDB, then inspect accepted rows, failed rows and the reasons they failed.
Works with MCP-compatible assistants — Claude Code, Claude Desktop, Cursor and others. No LakeLogic account required.
OLC defines the contract. Core executes it. MCP gives your assistant access to those tools.
Example¶
"Check orders.yaml, explain any findings, generate sample data and test it locally."
The assistant validates the contract, lints it, explains each finding, writes test data shaped by the contract, runs it, and reports which rows passed and why the others failed — real results from LakeLogic, not plausible-looking YAML.
The tools¶
| Ask | Tool |
|---|---|
| Does it match the OLC model? | validate_contract |
| Does it pass the lint checks? | lint_contract |
| Why is this rule flagged? | explain_rule |
| How is this part of a contract written? | contract_reference |
| Give me the ODCS version | export_odcs |
| Make me test data for it | generate_test_data |
| What happens when it runs? | run_contract |
Quick start¶
Start your assistant in the project that holds your contracts, then try the Walkthrough. Other clients: see Install. Before running contracts on real data, read Safety and privacy.