MCP App Store
by KeenEthics
Never86'd Marketplace Audit icon

Never86'd Marketplace Audit

By MYCHAEL DOUGLAS MUELLER

Get New App Alerts

Overview

Never86'd helps restaurant operators see what delivery apps charged and whether the payout math works. Upload a redacted statement or supported POS export to separate commission, fees, ads, restaurant-funded discounts, refunds, credits, and adjustments; compare matching periods; and see exactly what proof is still missing. It never asks for marketplace or bank logins and does not call something an overcharge without the contract and matching payout evidence. Built from firsthand operating work inside a 28-location, private-equity-backed restaurant group.

Tools

audit_marketplace_statement

ChatGPT
Use this when the user supplies one redacted CSV or TSV marketplace statement with explicit fee and funding columns. Detect marketplace and money columns, remove exact duplicates only when transaction identity supports it, calculate observed cost and payout variance, and return evidence-backed operator actions. For DoorDash, do not use Financial Simplified Transactions because Customer discounts does not identify who funded them; request Detailed Transactions or Payout Summary instead. For PDF, screenshot, or spreadsheet evidence, extract structured totals first and use reconcile_marketplace_payout. Do not use credentials or scrape a marketplace.

compare_marketplace_channels

ChatGPT
Use this when the user supplies two to six marketplace channel summaries for the same date range and identical restaurant scope. Compare eligible sales, true marketplace cost, all-in take rate, supported addressable leak, and payout variance. Do not use for month-to-month analysis; return a blocker rather than declaring a winner when scopes differ.

compare_marketplace_periods

ChatGPT
Use this when the user supplies two to twenty-four finalized, non-overlapping monthly statement summaries from the same marketplace and identical restaurant scope. Return chronological true-cost and take-rate trends, disclosure warnings, and evidence gaps without claiming causation or recovered cash. Do not use for cross-channel ranking or mismatched scopes.

inspect_pdq_z_report

ChatGPT
Use this when the user supplies one redacted daily PDQ Z-report as a native-text PDF or plain-text export. Extract daily aggregate POS evidence only. Never attribute PDQ Delivery to DoorDash, Uber Eats, or Grubhub, and never treat it as marketplace fee or payout proof. Do not use for image-only PDFs, credentials, guest data, or multi-day order matching.

inspect_toast_order_details

ChatGPT
Use this when the user supplies a redacted Toast OrderDetails.csv plus the exact location, business date, IANA timezone, and business-day cutoff. Classify a marketplace row only when at least two channel signals agree; quarantine incomplete, conflicting, out-of-scope, or wrong-location rows. Return POS Amount evidence, not gross sales, marketplace fees, or payout proof. Do not use if Tab Names, guest data, credentials, or payment-card fields remain.

reconcile_marketplace_payout

ChatGPT
Use this when ChatGPT has already extracted one marketplace statement scope from a redacted PDF, screenshot, spreadsheet, or typed evidence. Calculate true marketplace cost and reconcile expected payout. Include filename/page provenance, omit unreadable lines, and use zero only when the source explicitly shows zero or a disclosed bundled fee. Do not use credentials or invent missing values.

render_marketplace_audit

ChatGPT
Use this only after a Never86'd inspection, audit, reconciliation, or comparison tool returns a completed report. Pass that exact report without recalculating, summarizing, adding, or altering any value. Do not use with hand-authored or unrelated financial data.

Capabilities

Interactive

Example Prompts

Click any prompt to copy it.

Similar Apps