Deterministic ADV screening calculator for FLSA enterprise-coverage triage. Encodes Methods 1-4 (per-employee, capacity-derived, chain per-unit, format default), the geographic multiplier, ±40% range math, and the $500,000 FLSA flag (Above / Below / Borderline / Insufficient Data). NOT a coverage...
AI agents call adv_estimate to retrieve information from DOL WHD MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a deterministic calculation engine for Fair Labor Standards Act (FLSA) enterprise-coverage triage. It retrieves or accepts input parameters and outputs a screening classification. The explicit disclaimer 'NOT a coverage determination — screening signal only' confirms this is an analytical/advisory tool with no binding effects or side effects on external systems.
From the tool's definition Tool performs 'Deterministic ADV screening calculator' that 'Encodes Methods 1-4' and provides 'screening signal only.
Attacks that exploit this kind of access
Deterministic ADV screening calculator for FLSA enterprise-coverage triage. Encodes Methods 1-4 (per-employee, capacity-derived, chain per-unit, format default), the geographic multiplier, ±40% range math, and the $500,000 FLSA flag (Above / Below / Borderline / Insufficient Data). NOT a coverage determination — screening signal only. Method selection priority: chain per-unit ADV > employee count > capacity input > format default. Method 2 capacity input priority (highest first): seatCount > occupantLoad (×0.85 → seats) > squareFootage (BOH subtract + IBC 15-sqft-per-occupant + ×0.85) > parkingSpaces (× format-typical seats-per-space). Always pass capacitySource so the audit trail records where the number came from. Best practice: read employeeCount from osha_inspection_search results and pass it in here when an OSHA inspection record exists for the establishment (employee_count is a required OSHA field). Returns separate columns for estimate, range, method, capacity_input, capacity_source, flsa_flag, confidence, and a derivation-chain notes string. It is categorised as a Read tool in the DOL WHD MCP MCP Server, which means it retrieves data without modifying state.
Register the DOL WHD MCP server in PolicyLayer and add a rule for adv_estimate: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches DOL WHD MCP. Nothing to install.
adv_estimate is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the adv_estimate rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for adv_estimate. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
adv_estimate is provided by the DOL WHD MCP server (uhq-actual/dol_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →