Introduction
Profit optimisation for ecommerce advertising. Set it up from your AI assistant or in the app.
Product Metrics sends every paid order server-side to Google Ads, Meta and ChatGPT Ads with its revenue, profit, new or returning customer and lifetime value, so your campaigns bid on profit. Connect it to your AI assistant and it sets itself up, reads your campaigns and explains what changed.
Get started
ChatGPT: turn on Developer mode under Settings → Apps → Advanced settings, click Create app, paste the URL below and choose OAuth. Codex: run this in your terminal, then codex mcp login product-metrics.
codex mcp add product-metrics --url https://www.productmetrics.io/mcpOpen Add custom connector, name it Product Metrics and paste the URL below. Click Connect and sign in. It also works in Claude Desktop, Cowork and the Code tab.
Run this in your terminal, then enter /mcp in Claude Code and complete the Product Metrics sign-in.
claude mcp add --transport http product-metrics https://www.productmetrics.io/mcpAdd to Cursor opens the install dialog. Confirm it, then sign in from Cursor’s MCP settings.
Add to VS Code installs the server. Sign in to Product Metrics when VS Code asks.
Using another MCP client? Point it at:
https://www.productmetrics.io/mcpOther ways to get started
Or paste this into your coding agent:
Set up Product Metrics for my store. Read https://www.productmetrics.io/docs/llms.txt first.
If the productmetrics CLI is installed, run "productmetrics help agents" and pass --json to every productmetrics command. Otherwise use the Product Metrics MCP server: https://www.productmetrics.io/mcp
Start with my setup status, then take me through each open step. When a step needs me in a browser, give me the link and wait.What can Product Metrics do?
Server-side, adblocker-proof conversion tracking on your own domain.
Hashed customer data with each order, only when the visitor consents.
Bid on the profit of each order, or its revenue, with a target ROAS.
Give first-time buyers higher priority than people who bought before.
Steer on the revenue or profit your repeat buyers bring in.
Send customer lifetime value with each order and bid on it.
Customer Match lists in Google Ads, kept up to date after every order.
Each channel gets only what the visitor allowed.
Profit per order from product costs and your additional costs.
Eight Google Ads conversion actions, created for you as secondary.
Stores: Shopify, WooCommerce, Magento, Lightspeed, Shopware and any website through Cloudflare. Channels: Google Ads, Meta and ChatGPT Ads.
How it works
Full Signal Tracking sees the visit on your own domain, your shop confirms the paid order from its own data, and only then does Product Metrics work out the values and send them from its server. You don’t place a Google tag or write code.
Each order passes five stages: observe, confirm, consent, classify (new or returning) and value. Details: How it works.
Conversion values
Every paid order is sent as several conversions, one per value, so you choose which one bidding steers on:
Order #1042 €108.00, first paid order from this customer
→ Revenue 108.00, Profit 48.46
→ New Customer 108.00, New Customer Profit 48.46Bid on revenue with a target ROAS, or on profit (POAS). Where each value comes from: Conversion values.
Check your setup
One read tells you where setup stands and the next step, from the CLI, your assistant or the API:
productmetrics setup get-status --jsonThe response lists your workspaces and stores with the next action for each. See Get setup status.
Resources
Every public API operation, with examples.
productmetrics for scripts, CI and coding agents.
Task instructions your agent loads to set up tracking and analyse campaigns.
How Product Metrics handles your store and customer data.
Pricing, platforms and the blog.