mcpField
L
ll144-bias-audit-mcp

ll144-bias-audit-mcp

Local
github.com/CSOAI-ORGLegal & Government0Updated 18w ago
Repository

About ll144-bias-audit-mcp

ll144-bias-audit-mcp is an MCP server for auditing Automated Employment Decision Tools under NYC Local Law 144. It calculates selection rates and impact ratios, creates a publishable summary, and checks procedural requirements.

Key features

  1. 01Selection rates by group
  2. 02Impact ratio and 4/5ths rule flagging
  3. 03Publishable audit summary
  4. 04Procedural compliance checks

Use cases

  1. 01Auditing AEDT selection outcomes
  2. 02Preparing a Local Law 144 public summary
  3. 03Checking audit and candidate-notice requirements

MCP support

The server exposes tools to calculate bias-audit metrics, generate a summary, and check Local Law 144 procedural requirements.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "csoai-org-ll144-bias-audit": {
      "command": "uvx",
      "args": [
        "ll144-bias-audit-mcp"
      ]
    }
  }
}
Run commanduvx ll144-bias-audit-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypill144-bias-audit-mcp0.1.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

ll144-bias-audit-mcp

NYC Local Law 144 requires an independent annual bias audit of any Automated Employment Decision Tool (AEDT), with a published summary, before use. This computes the required metrics and signs the result. CSOAI Layer-0.

Tools

  • run_bias_audit(category, groups) — selection rate + impact ratio per group; flags impact ratio < 0.80 (4/5ths rule)
  • generate_ll144_summary(audits, tool_name, audit_date) — the publishable summary + overall compliance
  • check_compliance(...) — the procedural requirements (independent audit, published summary, candidate notice, ≤12 months)

Recurring, legally-required (DCWP-enforced). Apache-2.0.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.