MCP App Store
by KeenEthics

Overview

Tool4seller connects Claude to your authorized Amazon seller data through a secure, read-only connector. Ask Claude to analyze sales and profit performance, review advertising campaigns and targeting metrics, monitor inventory and inventory alerts, inspect sales traffic, track product reviews, and check FBA inbound shipments across your connected Amazon stores. The connector supports store-level and product-level reporting, multi-store comparisons, advertising performance analysis, and advanced targeting searches using metrics such as clicks, orders, ACoS, CTR, and conversion rate. Access is authorized through OAuth and limited to the stores and permissions available in your Tool4seller account. The connector is read-only: it does not modify Amazon listings, inventory, orders, campaigns, bids, or budgets.

Tools

apply_ad_group_changes

ChatGPT
Executes only a confirmed AD_AD_GROUP_CHANGE plan on the authorized Amazon Ads account. Changes ad-group default bids, states, or names. Requires the plan's one-time confirmation receipt and an idempotency key. A linked structure draft may automatically prepare the next preview without confirming or executing it. Review Sandbox simulates advertising writes and skips continuation.

apply_ad_group_creation

ChatGPT
Executes only a confirmed AD_AD_GROUP_CREATE plan on the authorized Amazon Ads account. Creates advertising ad groups. Requires the plan's one-time confirmation receipt and an idempotency key. A linked structure draft may automatically prepare the next preview without confirming or executing it. Review Sandbox simulates advertising writes and skips continuation.

apply_campaign_changes

ChatGPT
Executes only a confirmed AD_CAMPAIGN_CHANGE plan on the authorized Amazon Ads account. Changes campaign budgets, states, or names. Requires the plan's one-time confirmation receipt and an idempotency key. A linked structure draft may automatically prepare the next preview without confirming or executing it. Review Sandbox simulates advertising writes and skips continuation.

apply_campaign_creation

ChatGPT
Executes only a confirmed AD_CAMPAIGN_CREATE plan on the authorized Amazon Ads account. Creates Sponsored Products campaigns. Requires the plan's one-time confirmation receipt and an idempotency key. A linked structure draft may automatically prepare the next preview without confirming or executing it. Review Sandbox simulates advertising writes and skips continuation.

apply_keyword_rank_competitor_replacement

ChatGPT
Executes only a confirmed plan matching this tool in the authorized tool4seller account; rejects other operation groups. Replaces the full associated competitor set of one existing owned-product tracker. An empty set clears associations. Does not create independent competitor tracking or change keyword status. Requires the plan's one-time confirmation receipt and idempotency key; rechecks applicable eligibility and quota before applying. Revalidates applicable competitor Catalog relationships. Review Sandbox simulates execution.

apply_keyword_rank_tracking_changes

ChatGPT
Executes only a confirmed plan matching this tool in the authorized tool4seller account; rejects other operation groups. Updates existing keyword tracking status to ACTIVE (resume) or ARCHIVED (remove while retaining ranking history). Does not create tracking or change competitor associations. Requires the plan's one-time confirmation receipt and idempotency key; rechecks applicable eligibility and quota before applying. Does not access Amazon Catalog. Review Sandbox simulates execution.

apply_keyword_rank_tracking_creation

ChatGPT
Executes only a confirmed plan matching this tool in the authorized tool4seller account; rejects other operation groups. Creates keyword tracking for owned products or independent competitors. Existing active tracking is unchanged; paused tracking must use the status changes tool. Requires the plan's one-time confirmation receipt and idempotency key; rechecks applicable eligibility and quota before applying. Revalidates applicable competitor Catalog relationships. Review Sandbox simulates execution.

apply_product_ad_changes

ChatGPT
Executes only a confirmed AD_AD_CHANGE plan on the authorized Amazon Ads account. Changes advertising ad states or supported Sponsored Brands ad names. Requires the plan's one-time confirmation receipt and an idempotency key. A linked structure draft may automatically prepare the next preview without confirming or executing it. Review Sandbox simulates advertising writes and skips continuation.

apply_product_ad_creation

ChatGPT
Executes only a confirmed AD_AD_CREATE plan on the authorized Amazon Ads account. Creates Sponsored Products product ads or Sponsored Display product ads. Requires the plan's one-time confirmation receipt and an idempotency key. A linked structure draft may automatically prepare the next preview without confirming or executing it. Review Sandbox simulates advertising writes and skips continuation.

apply_targeting_changes

ChatGPT
Executes only a confirmed AD_TARGETING_CHANGE plan on the authorized Amazon Ads account. Changes positive keyword or ASIN targeting bids or states, or re-enables/archives negative keyword or ASIN targeting. Negative targeting has no bid actions; archiving is irreversible. Requires the plan's one-time confirmation receipt and an idempotency key. A linked structure draft may automatically prepare the next preview without confirming or executing it. Review Sandbox simulates advertising writes and skips continuation.

apply_targeting_creation

ChatGPT
Executes only a confirmed AD_TARGETING_CREATE plan on the authorized Amazon Ads account. Creates positive keyword, positive ASIN, negative keyword, or negative ASIN targeting entities. A batch may contain multiple targeting groups. Requires the plan's one-time confirmation receipt and an idempotency key. A linked structure draft may automatically prepare the next preview without confirming or executing it. Review Sandbox simulates advertising writes and skips continuation.

cancel_workflow_plan

ChatGPT
Cancels a prepared or confirmed plan before business changes are applied.

confirm_workflow_plan

ChatGPT
Confirms the exact immutable plan the customer reviewed. Call only after explicit customer approval of old/new values.

continue_workflow_draft

ChatGPT
Resumes a READY AD_STRUCTURE_CREATE draft from persisted server state. This call may query Amazon Ads for keyword or ASIN candidates and suggested bids, including candidates not yet created in the account, or reuse saved recommendations. It persists workflow progress and decisions. It reconciles the last atomic plan, retains successful Amazon IDs, and prepares exactly the next Campaign, Ad Group, Product Ad, automatic-target bid, or Targeting plan. All Campaigns are prepared together, then all Ad Groups, then all Product Ads across every ad group in one multi-group plan; the Product Ad plan is completed before any targeting recommendation or bid decision can pause another structure. It never confirms or applies a write plan. For AUTO ad groups it persists the selected bid mode with the created adGroupId, synchronizes the four Amazon-created targets, obtains suggested bids when selected, and returns a separately confirmable AD_TARGETING_CHANGE plan. Partial writes retry only failed items. A 429 suggestion read includes per-target evidence; ambiguous create results require reconciliation and are never retried. For MANUAL ad groups without supplied positive targeting, it waits until Product Ads exist, persists Amazon candidates only for the recorded KEYWORD or ASIN TARGET family, accepts customer selection by candidateRef, obtains suggested or custom bids, accepts explicit customCandidates when recommendations are absent or rejected, and prepares separately confirmable Targeting plans. It accepts at most 100 selected candidates per ad group and reuses the exact suggested bids already shown to the customer. Once every manual decision is ready, it combines all MANUAL positive targeting groups into one batch plan, then combines all configured negative targeting across AUTO and MANUAL groups into one separate batch plan. AUTO-only drafts skip MANUAL processing and MANUAL-only drafts skip AUTO processing. When a plan is returned, pass applyContinuation unchanged to the matching operation-specific execution tool so a successful write automatically returns the next stage preview without asking the customer to advance. After an AUTO bid write, immediately present the returned MANUAL targeting preview or selection action in the same response when manual groups remain.

diagnose_ad_efficiency

ChatGPT
Diagnoses advertising efficiency with read-only advertising metrics for one store and business date range.

diagnose_profit_anomaly

ChatGPT
Diagnoses profit anomalies with read-only profit, sales, and advertising signals for one store and business date range.

diagnose_sales_change

ChatGPT
Diagnoses sales changes with read-only sales, traffic, advertising, and inventory signals for one store and business date range.

discover_capabilities

ChatGPT
Discovers read-only Tool4seller MCP workflow capabilities, related tools, required inputs, and suggested next queries for business diagnosis tasks.

get_current_user

ChatGPT
Returns the current user's default currency, time zone, display language, and creation time.

get_workflow_draft

ChatGPT
Returns the current owned workflow draft without modifying it, including its effective expiry state, optimistic-lock version, missing inputs, validation errors, recommended next actions, and persisted continuation state.

get_workflow_plan

ChatGPT
Gets a workflow plan without modifying it, returning its effective expiry state, persisted execution status, item errors, upstream diagnostics, and explicit old/new values. After a timeout or disconnected apply call, query this exact plan (or retry apply with the same idempotency key); never create a replacement plan until its outcome is terminal and any INDETERMINATE items have been reconciled.

inventory_risk_review

ChatGPT
Reviews inventory risk with read-only inventory and inventory alert signals for one store.

list_inbound_shipment_items

ChatGPT
Returns paginated FBA inbound shipment items for up to 100 shipment IDs.

list_inbound_shipments

ChatGPT
Returns paginated FBA inbound shipments for authorized sellers.

list_stores

ChatGPT
Returns sellers, marketplaces, SP API status, Advertising API status, and active status for the current user.

prepare_ad_group_changes

ChatGPT
Prepares an immutable, separately confirmable Amazon Ads plan. Changes ad-group default bids, states, or names. Persists an internal plan without changing advertising entities.

prepare_ad_group_creation

ChatGPT
Prepares an immutable, separately confirmable Amazon Ads plan. Creates advertising ad groups. Persists an internal plan without changing advertising entities.

prepare_campaign_changes

ChatGPT
Prepares an immutable, separately confirmable Amazon Ads plan. Changes campaign budgets, states, or names. Persists an internal plan without changing advertising entities.

prepare_campaign_creation

ChatGPT
Prepares an immutable, separately confirmable Amazon Ads plan. Creates Sponsored Products campaigns. Persists an internal plan without changing advertising entities.

prepare_keyword_rank_competitor_replacement

ChatGPT
Prepares and persists an immutable keyword-rank tracking change plan for explicit customer review. Replaces the full associated competitor set of one existing owned-product tracker. An empty set clears associations. Does not create independent competitor tracking or change keyword status. Does not apply tracking changes. Competitor validation may read fresh Amazon Catalog product relationships.

prepare_keyword_rank_tracking_changes

ChatGPT
Prepares and persists an immutable keyword-rank tracking change plan for explicit customer review. Updates existing keyword tracking status to ACTIVE (resume) or ARCHIVED (remove while retaining ranking history). Does not create tracking or change competitor associations. Does not apply tracking changes. Uses existing account tracking; does not access Amazon Catalog.

prepare_keyword_rank_tracking_creation

ChatGPT
Prepares and persists an immutable keyword-rank tracking change plan for explicit customer review. Creates keyword tracking for owned products or independent competitors. Existing active tracking is unchanged; paused tracking must use the status changes tool. Does not apply tracking changes. Competitor validation may read fresh Amazon Catalog product relationships.

prepare_product_ad_changes

ChatGPT
Prepares an immutable, separately confirmable Amazon Ads plan. Changes advertising ad states or supported Sponsored Brands ad names. Persists an internal plan without changing advertising entities.

prepare_product_ad_creation

ChatGPT
Prepares an immutable, separately confirmable Amazon Ads plan. Creates Sponsored Products product ads or Sponsored Display product ads. Persists an internal plan without changing advertising entities.

prepare_targeting_changes

ChatGPT
Prepares an immutable, separately confirmable Amazon Ads plan. Changes positive keyword or ASIN targeting bids or states, or re-enables/archives negative keyword or ASIN targeting. Negative targeting has no bid actions; archiving is irreversible. Persists an internal plan without changing advertising entities.

prepare_targeting_creation

ChatGPT
Prepares an immutable, separately confirmable Amazon Ads plan. Creates positive keyword, positive ASIN, negative keyword, or negative ASIN targeting entities. A batch may contain multiple targeting groups. Persists an internal plan without changing advertising entities.

prepare_workflow_draft

ChatGPT
Creates or incrementally updates an AD_STRUCTURE_CREATE draft. Collect the Sponsored Products Campaign/Ad Group/Product Ad structure and any targeting the customer already supplied. One MANUAL ad group can contain only one positive targeting family: KEYWORD or ASIN TARGET. If positive targeting is omitted, collect manualTargetingFamily=KEYWORD|TARGET before execution. If the customer wants both, model separate manual Campaign/Ad Group structures from the start and assign one family to each; never put both into one ad group. Every ad group needs a negative-targeting decision: supplied allowed negative items automatically record negativeTargetingMode=CONFIGURED; when none are supplied, recommend negatives and ask the customer to choose CONFIGURED or NONE. AUTO permits both negative keywords and negative ASINs; a MANUAL KEYWORD group permits only negative keywords, and a MANUAL TARGET group permits only negative ASINs. Continuation prepares all Campaigns together, then all Ad Groups, then all Product Ads across every ad group in one multi-group plan before any AUTO bid decision or MANUAL recommendation can pause the draft. After all Product Ads exist, continuation queries and persists Amazon recommendations only for each manual ad group's recorded family, asks the customer to choose up to 100 candidates, obtains suggested or custom bids, then combines all ready MANUAL positive targeting into one Targeting batch plan. It subsequently combines every configured negative targeting item across AUTO and MANUAL structures into one separate negative Targeting batch plan. AUTO-only drafts skip the MANUAL stage and MANUAL-only drafts skip the AUTO stage. If recommendations are absent or rejected, submit customer-approved customCandidates of the same family to the continuation; do not recreate the already-created structure. For every AUTO ad group, explain that Amazon creates exactly four targets after the ad group exists and record automaticTargetBidding.mode as KEEP_DEFAULT, AMAZON_SUGGESTED, CUSTOM, or DECIDE_LATER; CUSTOM requires all four official theme bids. Never model those themes as manually created targets. Every supplied nested entity requires a stable clientRef. Updating requires draftId and expectedDraftVersion; arrays merge by clientRef and remove only through removeClientRefs. When the draft is READY, call continue_workflow_draft. The server then persists the current atomic plan, created Amazon IDs, recommendation choices, and bid choice so later calls safely resume. Every returned write plan must still be shown, explicitly confirmed, and applied. Pass applyContinuation to the matching operation-specific execution tool so successful writes automatically prepare the next stage; never ask the customer for permission merely to advance. Recommendation 429 responses are recoverable and do not create a write plan. During draft collection, accept syntactically valid SKU/ASIN values without querying Inventory or Listings; production Product Ad plan preparation performs product resolution.

query_aba_search_terms

ChatGPT
Query the latest Amazon Brand Analytics search-term report for one supported marketplace: US ATVPDKIKX0DER, CA A2EUQ1WTGCTBG2, UK A1F83G8C2ARO7P, DE A1PA6795UKMFR9, FR A13V1IB3VIYZZH, IT APJ6JRA9NG5V4, ES A1RKKUPIHCS9HS, JP A1VC38T7YXB528. Returns the current-week report plus raw previousWeek (1 week earlier), sameWeekLastMonth (4 weeks earlier), and sameWeekLastQuarter (12 weeks earlier) snapshots (rank, click share, conversion share) and the latest 13 weekly rank points. Comparison snapshots are raw baselines, not calculated changes or rates. BROWSE is paginated. EXACT accepts 1 to 100 terms and FUZZY accepts one keyword; neither accepts pagination or sorting, and FUZZY returns at most the first 100 Lucene matches. searchFrequencyRank is the weekly search rank. searchVolume is weekly search volume. totalClickShare and totalConversionShare are percentages from 0 through 100, not counts or decimal fractions. Trend point weekStartDate is the week start date. supplyDemandRatio is searchVolume divided by competingListingCount (searches per competing listing), not a percentage. query.status is MATCHED when at least one item matched and NO_MATCH otherwise; inspect each item.matched for per-term results. pagination is present only for BROWSE and contains offset and limit but no total or hasMore. This is marketplace research data, not keyword-rank tracking or advertising search-term performance.

query_account_usages

ChatGPT
Queries current account-wide package limits, usage and remaining capacity. Authenticated basic access; no business OAuth scope is required. Omit resources for all resources, including businesses whose operational APIs are not yet available. Use when asked about quota or before planning capacity-consuming changes. Results do not reserve capacity or guarantee a later write. NOT_APPLICABLE is not unlimited; UNAVAILABLE is not zero. Business lists do not include package quotas. Use KEYWORD_RANK_TRACKING_KEYWORDS for keyword rank tracking; active site/keyword pairs are deduplicated across account shops and parent ASINs. Paused records do not consume keyword capacity.

query_advertising

ChatGPT
Returns store-level advertising performance or paginated advertising performance metrics grouped by SKU, ASIN, or parent ASIN for a single store and business date range.

query_advertising_ad_groups

ChatGPT
Returns current advertising ad groups with stable IDs, name, state, serving status, default bid, parent campaign including campaignType, and Amazon createdAt/updatedAt timestamps as UTC ISO-8601 instants. Results can proceed to AD_AD_GROUP_CHANGE, AD_AD_CREATE, or AD_TARGETING_CREATE. AD_AD_CREATE resolves the product-specific creative: SP uses PRODUCT_AD/productCreative and SD uses COMPONENT/responsive eCommerce componentCreative. Choose targeting inputs from campaign.campaignType: Sponsored Display supports ASIN Targets and negative ASIN Targets only, never keywords or negative keywords.

query_advertising_ads

ChatGPT
Returns current Sponsored Products, Sponsored Display, and Sponsored Brands ads with stable ad IDs, product identity or name, state, serving status, parent references, and Amazon createdAt/updatedAt timestamps as UTC ISO-8601 instants. Results can proceed to AD_AD_CHANGE for confirmed ENABLED/PAUSED state changes or Sponsored Brands name changes.

query_advertising_bid_recommendations

ChatGPT
Read-only POST that returns current Amazon suggested bids and bid ranges for 1 to 100 Sponsored Products, Sponsored Brands, or Sponsored Display targeting items. For an existing keyword or target, provide targetingType and targetingId only. For a candidate that has not been created, first create its ad group, then provide targetingType, adGroupId, and targeting; this operation does not create the candidate. The server resolves the advertising product, Campaign, and Ad Group from synchronized data, so clients do not provide adProduct or campaignId. Compatible items in the same product, Campaign, Ad Group, and targeting type are combined into one Amazon recommendation request. Successful group responses are cached briefly and reused for identical requests. If a group is rate-limited, earlier successful groups are preserved, later groups of the same advertising product are not sent, and other advertising products continue. Retry only retryItemIndexes after retryAfterSeconds; do not immediately repeat the complete request when requestFingerprint is unchanged. Rate-limited and deliberately skipped unfinished items both retain the backward-compatible TOO_MANY_REQUESTS code; details distinguish them. Retrieves bid recommendations from Amazon Ads using the authorized advertising profile, or reuses cached recommendation results. Supports existing targets and supplied keyword or product targeting candidates that have not been created in the advertising account. This is a read-only tool: it neither creates targeting entities nor applies the returned bid. Use it when a bid decision needs Amazon's recommendation; historical CPC is not a suggested bid. Never repeat an unchanged request in the same assistant turn. Reuse successful items and the same requestFingerprint response. On TOO_MANY_REQUESTS, wait at least retryAfterSeconds and call this tool again with only retryItemIndexes.

query_advertising_campaigns

ChatGPT
Returns advertising campaign performance or daily campaign performance.

query_advertising_negative_targets

ChatGPT
Returns paginated negative keyword or negative ASIN management records with stable IDs, state, serving status, match details, parent campaign/ad group references, and Amazon createdAt/updatedAt timestamps as UTC ISO-8601 instants. Historical ENABLED, PAUSED, and ARCHIVED states remain queryable. Results can proceed to AD_TARGETING_CHANGE to re-enable legacy PAUSED entities or archive PAUSED/ENABLED entities; PAUSED is not a writable target state, ARCHIVED is terminal, and negative targeting entities do not support bid actions or performance metrics.

query_advertising_portfolios

ChatGPT
Returns current Amazon Ads portfolios with stable portfolio IDs, names, states, serving status, budget policy and amount, budget dates, in-budget status, and Amazon createdAt/updatedAt timestamps as UTC ISO-8601 instants. This management query does not return performance metrics.

query_advertising_purchased_products

ChatGPT
Returns purchased product performance attributed to advertised products.

query_advertising_search_terms

ChatGPT
Returns advertising search terms or search term purchased products.

query_advertising_target_recommendations

ChatGPT
Read-only POST that returns Amazon-recommended keyword or ASIN targeting candidates before targeting entities are created. Supply exactly one source: adGroupId, or asins with adProduct. With adGroupId, the server resolves Campaign, advertising product, advertised ASINs, Sponsored Brands creative context, and Sponsored Display tactic from synchronized data. Sponsored Products supports KEYWORD and TARGET recommendations, Sponsored Brands supports KEYWORD and TARGET recommendations, and Sponsored Display supports TARGET recommendations only. Sponsored Display ASIN product recommendations require tactic T00020 because Amazon v3.3 does not support PRODUCT recommendations for T00030. TARGET currently means recommended ASIN product targets; category, brand, and audience recommendations are not included. Sponsored Products and Sponsored Brands TARGET responses can return nextToken for the next page. Pass that token back unchanged while keeping the original recommendation context. If Amazon rate-limits any page, the server does not retry and returns HTTP 429 with code TOO_MANY_REQUESTS; retain previously received items and retry only the failed page with the same nextToken. Each returned targeting object can be copied into a candidate bid-recommendation item together with the created adGroupId and targetingType, then used to create the selected target. This operation does not create or update advertising entities. Recommendations are retrieved from the Amazon Ads recommendation APIs using the authorized advertising profile and supplied context. Returned candidates are not limited to targeting entities already present in the user's advertising account. Use this tool first when the customer has not selected targeting candidates, then pass selected targeting objects to query_advertising_bid_recommendations before creation.

query_advertising_targets

ChatGPT
Returns advertising keyword target or ASIN target performance.

query_asin_search_terms

ChatGPT
Look up natural search terms for a marketplace ASIN. The ASIN may be a variation parent, child, or standalone product; callers do not need to know its type. For a parent, returns child ASINs and each child's available search-term count; ask which child the user means, then call this same tool for that child. For a child or standalone ASIN, SUMMARY (default) returns the first 100 terms in PC order; FULL returns the complete available list. If the user explicitly requests all terms, use FULL on the first call for the selected child. naturalIdx is this ASIN's natural rank; searchFrequencyRank is the keyword's ABA weekly search rank. searchVolume is weekly search volume. This tool does not return advertising bids or keyword trends; use an ABA tool for a selected keyword's weekly trend. If variation lookup is unavailable, variationType is UNKNOWN, not a claim that the ASIN is standalone.

query_inventory

ChatGPT
Returns paginated inventory listing data for a single store. FBA-specific fields are populated only for AFN inventory and are null for MFN inventory when not applicable.

query_inventory_alerts

ChatGPT
Returns low stock, excess stock, long-term storage, or recommended removal inventory alerts.

query_keyword_rank_trackers

ChatGPT
One trackingScope per request: PARENT (default) uses parentAsin and tracks the family; CHILD uses asin and tracks only that exact variation, excluding siblings. The server resolves its parent. For tracker lists use parentAsins with PARENT or asins with CHILD. Query, ADD, RESUME, REMOVE and SET_COMPETITORS must preserve the same scope and target. Both OWN_PRODUCT and independent COMPETITOR support CHILD. For OWN_PRODUCT associations, PARENT competitorAsins are parent/standalone ASINs while CHILD competitorAsins are exact variation ASINs. includeCompetitors compares the same scope. Account capabilities and notices are returned even for empty results. Check advertisingRankTracking before interpreting advertising ranks or offering advertising tracking. False means unsupported, not a missing match; never promise advertising ranks or silently substitute organic tracking for an explicit advertising-rank request. This applies to own products, independent competitors, and associated competitors. Returns keyword rank tracking configuration across authorized stores. Groups top-level items by storeId and the selected tracking target with nested keywords, and may include PENDING_KEYWORDS parents. Each tracking record has a stable trackingId and its own ACTIVE or PAUSED state. PAUSED means the system stopped tracking due to package expiry or restrictions; it is not a customer pause action. Restore it with RESUME only when package access and quota permit. Returns all matching configuration without pagination. Product title and imageUrl are included when available. Latest rankings are not included; use query_keyword_rank_trends with storeId, parentAsin and keywords to retrieve rankings. This tool does not return Search Volume or calculate rank changes. Query query_account_usages with resources=[KEYWORD_RANK_TRACKING_KEYWORDS] for account quota; list counts are not quota usage. One product type per request: OWN_PRODUCT (default) or independent COMPETITOR. Call separately for each type; ALL and mixed selections are not supported. Competitors share account-wide marketplace/keyword quota with owned products. To create tracking use prepare_keyword_rank_tracking_creation; to resume or archive existing keywords use prepare_keyword_rank_tracking_changes; to replace associated competitors use prepare_keyword_rank_competitor_replacement. Follow each published schema and obtain explicit customer confirmation before its matching apply tool. Preserve the returned trackingScope: PARENT uses parentAsin; CHILD uses asin. Never substitute the parent when a customer requests one child.

query_profit

ChatGPT
Returns store-level profit summaries or paginated profit data by SKU, ASIN, or parent ASIN for a single store and business date range.

query_review_ratings

ChatGPT
Returns paginated rating data for parent ASINs that have review tracking enabled in a single store. Parent ASINs without review tracking or rating data are omitted from the response.

query_sales

ChatGPT
Returns sales summaries, daily sales summaries, SKU sales, or daily SKU sales for a business date range.

query_sales_orders

ChatGPT
Returns one store's sales orders with all order items in descending purchase time. Uses a UTC start-inclusive, end-exclusive window of at most 31 days. Excludes canceled, non-Amazon and replacement orders. SKU and promotion filters select whole orders. The time window always filters purchasedAt (order purchase time), never refund or return event time. REFUND means the order currently has a refund flag in the latest synchronized data; it does not necessarily mean a full refund or a physical return. An order purchased in July and refunded in September matches a July purchase window with REFUND, but not a September purchase window. Historical results may change after later refunds are synchronized. This endpoint cannot answer which refunds or returns occurred during a period. Amounts may be estimated; amounts after promotion are not settlement proceeds. Missing prices or order currency produce null amounts. Use this endpoint for individual orders and their items; use Sales reports for aggregated sales metrics and Profit reports for profit, refunds and costs. Order amount sums are not guaranteed to reconcile with report sales or netSales. Returns no total count. Offset pagination is not a snapshot; deduplicate by storeId and orderId when collecting changing data.

query_sales_traffic

ChatGPT
Returns sales traffic summaries or paginated sales traffic metrics by ASIN or parent ASIN for a single store and business date range.

query_store_health

ChatGPT
Runs a read-only store health check by combining sales, profit, advertising, and inventory signals for one store and business date range.

diagnose_ad_efficiency

Claude

diagnose_profit_anomaly

Claude

diagnose_sales_change

Claude

discover_capabilities

Claude

get_current_user

Claude

inventory_risk_review

Claude

list_inbound_shipment_items

Claude

list_inbound_shipments

Claude

list_stores

Claude

query_advertising

Claude

query_advertising_campaigns

Claude

query_advertising_purchased_products

Claude

query_advertising_search_terms

Claude

query_advertising_targets

Claude

query_inventory

Claude

query_inventory_alerts

Claude

query_profit

Claude

query_review_ratings

Claude

query_sales

Claude

query_sales_traffic

Claude

query_store_health

Claude

Capabilities

Writes

Similar Apps