English Français العربية

io.github.LakeLogic/lakelogic-mcp

Official registry Developer tools

Validate, lint, test-run and explain Open Lakehouse Contracts with LakeLogic, from any AI assistant.

Source code Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

PYPI package lakelogic-mcp
Claude Code 
claude mcp add lakelogic-mcp -- uvx lakelogic-mcp==0.1.4
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "lakelogic-mcp": {
            "command": "uvx",
            "args": [
                "lakelogic-mcp==0.1.4"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. LakeLogic MCP
  2. Example
  3. Tools
  4. Install
  5. Safety and privacy
  6. Contributing

LakeLogic MCP

mcp-name: io.github.LakeLogic/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.

📖 Documentation: https://mcp.lakelogic.io/

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.

Tools

ToolAnswers
validate_contractDoes it match the OLC model? Each error's location and problem
lint_contractDoes it pass the lint checks? Governance findings, each with its fix
explain_ruleWhy does a lint rule exist? What it checks, why it matters, a failing and a fixed contract
contract_referenceHow is one part of a contract written? (anatomy, quality, materialization, …)
export_odcsThe contract as an Open Data Contract Standard document
generate_test_dataSynthetic data shaped by the contract, with a share of rows that deliberately break its rules
run_contractHow many rows pass, how many fail, and why (Polars or DuckDB, on a local file)

Details and inputs: Tools. A first run, start to finish: Walkthrough.

Install

All clients need uv on your PATH. Start your assistant in the project that holds your contracts (or pass --root <folder>).

Claude Code — as a plugin:

/plugin marketplace add LakeLogic/lakelogic-mcp
/plugin install lakelogic-mcp@lakelogic-mcp

or directly: claude mcp add lakelogic -- uvx lakelogic-mcp

Cursor: Add to Cursor

Claude Desktop, VS Code and other MCP clients — add to the client's MCP settings:

{
  "mcpServers": {
    "lakelogic": {
      "command": "uvx",
      "args": ["lakelogic-mcp", "--root", "/path/to/your/contracts/project"]
    }
  }
}

It is listed in the official MCP Registry as io.github.LakeLogic/lakelogic-mcp.

Safety and privacy

  • Local. The server talks to your client over stdio; it opens no network connection itself, needs no account and sends no telemetry. (Installing with uvx downloads the package, as any install does.)
  • Tool paths stay in your project. Every path you give a tool, and the _domain.yaml / _system.yaml that lint takes into account, must be inside the project folder. Files a contract itself names (a links: dataset, for example) are read by Core as written.
  • Running a contract does what the contract configures. If a contract declares notifications or run-log delivery, LakeLogic Core may send them during run_contract. Nothing is written to the contract's target.
  • Results reach your AI provider. Tool results go into the assistant's context: quarantined sample rows, failure reasons (which can quote your data) and the contract itself. sample: 0 removes only the rows, so test with generated data if a file holds personal or confidential data.

More: Safety and privacy.

Contributing

To work on the server from a checkout, see Development.

Frequently asked questions

What is io.github.LakeLogic/lakelogic-mcp?

Validate, lint, test-run and explain Open Lakehouse Contracts with LakeLogic, from any AI assistant.

How do I install io.github.LakeLogic/lakelogic-mcp?

It runs on your machine. In Claude Code: claude mcp add lakelogic-mcp -- uvx lakelogic-mcp==0.1.4. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.LakeLogic/lakelogic-mcp need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is io.github.LakeLogic/lakelogic-mcp open source?

Yes. Its code is on GitHub under the Apache-2.0 license.

Who maintains io.github.LakeLogic/lakelogic-mcp?

It is published by LakeLogic. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.