Ll144 Bias Audit Mcp

Computes NYC Local Law 144 AEDT bias-audit metrics — selection rates, 4/5ths impact ratios and a publishable summary — for an AI assistant.

What you can do

• Run a bias audit on hiring-tool outcome data by category and group, returning selection rates and impact ratios and flagging ratios below 0.80 under the 4/5ths rule.
• Generate a publishable audit summary for a named tool and audit date, with an overall compliance result.
• Check procedural compliance items such as an independent audit, a published summary, candidate notice and a cycle of 12 months or less.

When to use it

Use it when you need to audit an automated employment decision tool for New York City Local Law 144 and produce the annual summary that must be published before use, or to check whether those procedural requirements are met.

Requirements

Runs as a local process over stdio, installed from the PyPI package ll144-bias-audit-mcp and started with Python. No authentication, environment variables or headers are declared. Desktop only; not available as a web executable.