Skip to content
Product Metrics MCP

Product Metrics MCP server

Give Claude, ChatGPT, Claude Code or Cursor your store, product and Google Ads data, and let them run Product Metrics setup through the API.

The Product Metrics MCP server connects any MCP-compatible assistant to your Product Metrics account. Ask in plain words: the assistant picks the tools.

  • It reads your Google Ads account, your store and your products.
  • It can run Product Metrics setup for you through the public API: create a workspace, connect Google Ads, Merchant Center and your store, and change settings and product rules.

See the tools reference for exact names, inputs and results.

Connect

Add this remote MCP server to your client:

https://www.productmetrics.io/mcp

Your client opens Product Metrics in a browser. Check what the page says the app Can read and Can change, then sign in (or Continue with Google to create an account) and click Connect with the app’s name, such as Connect Claude.

Product Metrics uses OAuth, so no API key is required.

For client steps, see Setup and usage, or go straight to Claude, ChatGPT, Claude Code, Cursor or Codex. With the CLI, productmetrics mcp-config prints the URL and the steps for each client.

How workspaces and properties work

A workspace (company) is your business or an agency’s client. A property is one store with its Google Ads account inside a workspace. One connection covers every property you can open. See Workspaces and properties.

  • Analysis tools work on one property. The assistant calls list_properties, then passes the store’s propertyId as property_id to every other tool. With one property, it uses that one without asking. With several, it asks which store you mean or answers per store.

  • API tools work on your whole account. search and execute run without a property: the operations take companyId and propertyId in their paths, so the assistant can set up a new workspace before any property exists.

  • Pin one property for a script or agent that should only see one store:

    https://www.productmetrics.io/mcp?selectedAccountPropertyId=<propertyId>

    The analysis tools then take no property_id. Get the propertyId from list_properties.

Tools

Your assistant chooses these tools automatically. Use this table when you need the exact inputs and results. Every argument, default and limit is in MCP tools.

ToolUse it forInputsResult
list_propertiesThe stores you can openname_containsProperties with company, Google Ads customer id and currency
get_store_overviewHow the store is doing next to the adsdate_range, compare, breakdown, top_productsSessions, revenue, conversion rate, shop orders, new and returning customers, profit
explain_google_ads_changeWhy a Google Ads metric movedmetric, date_range, change_date, campaign_ids, campaign_types, campaign_name_containsThe change day, the funnel split, what carries it, account changes before it, store revenue next to it
get_google_ads_reportPerformance by campaign, product, device and morelevel, date_range, compare, breakdown, filters, sort_by, limitRows with clicks, cost, conversions, value and ROAS
get_poas_reportProfit on ad spendlevel, date_range, compare, campaign_ids, item_ids, only_unprofitable, sort_byCost, conversion value, ROAS, gross profit, POAS and profit after ads, with stock and decision per product
get_google_ads_changesThe account’s change historydate_range, campaign_ids, campaign_name_contains, limitWho changed what and when, with values before and after (last 30 days)
get_product_targetingListing groups per campaigncampaign_ids, campaign_name_contains, include_pausedWhich products each campaign targets
compare_product_segmentsSegments against the campaign setupdate_range, campaign_ids, campaign_types, compare_withSpend, value and ROAS per segment and per value of the other labels, per campaign
run_google_ads_queryA custom GAQL queryquery (required), max_rowsThe query rows
list_products_to_investigateProducts with a signal worth acting onsignal_kinds, action, sort, segment, category, limit, cursorProducts ranked by money at stake, with their decision and strongest signal
search_productsFind a product by name or idquery (required), limitMatching products with their item_id
get_product_contextEverything about a few productsitem_ids (required), detailThe five layers, the decision, signals and suggested labels, with contextVersion
summarize_groupsTotals per segment or categoryby (required), limitProducts, spend, conversion value, ROAS and decision mix per group
get_changesWhat changed since the last rungroup_by, limitLast week against the week before, top movers, signals that appeared or cleared
get_insightsStore insight cardsspots, feed_key, limitThe stored cards
get_highlightsProduct Segmentation highlightsNoneRevenue, ad spend and ROAS, and the spend going to Drainers
get_inventory_stateStock and reorder datesitem_ids, filter, limit, cursorUnits, weeks of cover, stockout and reorder dates
get_competitor_offersCompetitor prices for one productitem_id (required), daysEvery seller’s latest price and its gap to yours
get_product_timeseriesOne product’s historyitem_id (required), measures, days, grain, formatA daily or weekly series
get_group_timeseriesA group’s historyitem_ids, top_by, segment, category, measures, days, grainA daily or weekly series
get_segment_historyWhen a product changed segmentitem_id (required), daysSegment changes with dates
propose_changeFile a change for a person to approveitem_id, change, rationale, context_version (all required)The filed proposal
list_proposalsProposals and how metrics moved after themstatus, item_id, limitProposals with status and outcome
query_lakeA read-only SQL SELECT over the store’s datasql (required), max_rowsRows with the data age per source
searchFind a public API operationcode (required), truncateWhat your code returns from the OpenAPI document
executeCall the public APIcode (required), truncateWhat your code returns from codemode.request calls
send_product_metrics_feedbackTell the Product Metrics team what worked or failedsentiment, message, context, feature, actorReceipt

Every analysis tool except list_properties also takes property_id.

These tools read the Google Ads account linked to the property, live. They never change it.

  • Start with explain_google_ads_change for “why did … drop”. It answers in one call; use get_google_ads_report only to drill further.
  • get_poas_report is the profit view of the same account: cost against the profit from your store’s orders.
  • explain_google_ads_change and run_google_ads_query count towards the lower hourly limit for expensive tools, as does query_lake.
"Why did my Google Ads ROAS drop last week?"
→ list_properties, then explain_google_ads_change

Products and segments

These tools read Product Metrics data: segments, signals, stock and competitor prices.

  • Use list_products_to_investigate or search_products to find products, then get_product_context for the full picture.
  • Use summarize_groups for totals per segment or category, and get_changes for what moved since the last run.
  • get_product_timeseries, get_group_timeseries and get_segment_history show history.
"Which Stars are about to run out of stock?"
→ get_inventory_state with filter reorder_due, then get_product_context

Proposals

propose_change files a change (a Merchant Center custom label, a priority, or a task) for a person to approve in Priorities. Nothing is written to Merchant Center until a person approves it. list_proposals shows earlier proposals and, once measured, how the numbers moved in the 28 days after.

API tools: search and execute

search and execute give the assistant the whole public API in two tools (Code Mode). The assistant writes a short JavaScript function; Product Metrics runs it in a sandbox with no network.

  • search runs the code against the OpenAPI document, filtered to the operations your connection may call. Nothing is called and nothing changes.
  • execute runs the code with codemode.request({ method, path, query, body, idempotencyKey, ifMatch, confirm }). Each request runs as the matching CLI command would, with your role.
"Set up Product Metrics for my shop: create the workspace and
connect Google Ads."
→ search, then execute: GET /onboarding, PUT /onboarding/account-type,
  POST /onboarding/complete, POST /companies (with an idempotency key),
  GET /google-ads/accounts, POST /companies/{companyId}/google-ads/property-connections

Rules the server enforces:

  • An operation that deletes data runs only with confirm: true. The assistant asks you first.
  • A step only you can take (the Google grant, Shopify approval, checkout) returns a URL. The assistant gives it to you, waits, then reads the status again.
  • Secret fields, such as a store setup token, come back hidden. Read them in the Product Metrics app or with the CLI.
  • At most 25 requests per execute run. Results over about 6,000 tokens are cut; truncate: false allows up to 40,000 characters.

Access control

Product Metrics asks your permission once, on the consent page. It lists the scopes the client asks for; you allow them all or cancel.

ScopeThe consent page showsWhat it allows
mcpCan read: Google Ads, store and product data, to answer questions and suggest improvements you approveThe analysis tools and propose_change
readCan read: Google Ads, store and product data, to answer questionsAPI operations that read (x-scope: read)
setupCan change: Google Ads, Merchant Center, store and tracking connectionsAPI operations that connect accounts and stores
writeCan change: settings, product rules and feeds, and who has accessAPI operations that change settings, rules, feeds and invite people

Without setup or write, Can change says “Nothing in your account”.

  • Your role applies. The assistant acts as you, with your role in each workspace (admin, editor or viewer). Any member can use the analysis tools; only editors and admins can file proposals. Each API operation names the role it needs.
  • Your access is checked on every request. If you lose access to a workspace, the assistant loses it at once.
  • The analysis tools need Pro on the property and the MCP server turned on for your account. The API tools do not: a new account can set Product Metrics up through them.
  • Hourly limits. Up to 5,000 tool calls per person and 20,000 per property each hour; 30 and 120 for the expensive tools. API calls share the API rate limit.

Disconnect

Remove the connector in your client’s settings. To revoke the app’s tokens on the Product Metrics side as well, ask Product Metrics support: a revoke takes effect within about a minute.