AMZ Vault

Amazon Seller Central + Amazon Ads for AI clients. Settlement-accurate P&L (every fee, refund and reimbursement as Amazon actually posted it), full Sponsored Products/Brands/Display PPC management, Search Query Performance and Brand Analytics, inventory and restock, and per-ASIN forecasting. Every write stages a reviewable diff for human approval - no autonomous-write mode. OAuth 2.1 sign-in with your AMZ Vault account (comes with every trial). Live demo with no signup: https://amz-vault.com/demo

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://amz-vault--brdtt12.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "AMZ Vault": {
      "url": "https://amz-vault--brdtt12.run.tools"
    }
  }
}

能力清单

工具	说明
account_sellers	List the Amazon seller connections this token can access, with their marketplaces and currencies.
account_profiles	List the advertising profiles (PPC accounts) bridged to this token's seller connections.
data_describe	Without arguments: list every warehouse dataset available to data_query. With dataset_key: its columns, column descriptions, and a sample row.
data_freshness	Per-dataset sync freshness, row counts, date coverage and backfill progress — use to caveat answers correctly. Covers seller (SP-API) datasets AND advertising datasets (latest data date per raw PPC dataset for the resolved profile).
pnl_summary	Profit & Loss summary for a date window: account tiles (sales, fees, COGS, ad spend, gross profit, contribution margin, net profit, TACoS) plus the top product rows.
pnl_by_asin	Per-ASIN P&L rows for a date window (optionally one ASIN): sales, units, fees, COGS, margins, TACoS, stock.
pnl_breakdown	Settlement-basis account waterfall: revenue → refunds → COGS → gross profit → Amazon fees → contribution margin → advertising → net profit → expenses → net profit.
pnl_period_cards	The dashboard mini-P&L cards (Today / Yesterday / MTD / This-month forecast / Last month).
product_library	The canonical product catalog with breakeven ACoS and effective BE margin targets per product family.
product_fee_preview	Amazon's own estimated fees per SKU for the coming weeks (referral, fulfillment, storage).
product_cogs	Current per-SKU landed costs (COGS) and coverage summary.
inventory_health	FBA fulfillable/inbound/reserved units, aged inventory, restock recommendations and AWD pool per SKU. alert_type is derived (OUT_OF_STOCK / LOW_STOCK / AGED_STOCK) when Amazon's restock report has no alert; alerts_only=true returns just the flagged SKUs.
data_query	Generic query over any warehouse dataset (see data_describe): column projection, filters (eq/neq/gt/gte/lt/lte/in/contains), date bounds, ordering, limit ≤1000 + offset — page with offset until a short page comes back to retrieve FULL datasets. Tenancy is enforced automatically.
pnl_settlement_audit	Settlement fee audit: every distinct fee combination Amazon charged, classified into P&L buckets — verify nothing is misclassified or missed.
pnl_mcf_summary	Multi-Channel Fulfillment (off-Amazon) totals: units, orders, fulfillment fees and COGS for a window.
pnl_expenses	Custom operating expenses (subscriptions, VA, freight, 3PL…): scope, recurrence, amounts.
pnl_refunds	Refund components for a window: net refund amount, count, and itemized lines (reimbursements, restocking).
pnl_sb_attribution	Per-ASIN Sponsored Brands cost attribution (the sales-weighted split of campaign-level SB spend).
ppc_negatives	Current negative keywords and negative product targets (campaign- and ad-group-level), with state and source.
ppc_campaign_metadata	Campaign configuration and user metadata: bidding strategy, placement settings, goal/KPI, tags, notes.
ppc_placement_modifiers	Current placement bid modifiers per campaign (top of search, product pages, rest of search).
ppc_describe	Without arguments: catalog of the raw PPC datasets behind ppc_query (daily report tables at campaign/ad-group/target/search-term/placement/ASIN grain for SP+SB+SD, plus current-state snapshots: campaign_meta, portfolios, placement modifiers, SB ads/creatives, SD creatives, asset library, negative keywords/targets). With dataset_key: full column list + a sample row.
ppc_query	FULL-fidelity row-level query over any raw PPC dataset (see ppc_describe): column projection, filters (eq/neq/gt/gte/lt/lte/in/contains), date bounds, ordering, limit ≤1000 + offset — page with offset until a short page to retrieve complete datasets. This is the path for daily time series below account level, SB/SD keyword-level data, and anything the shaped ppc_* readers cap. Profile tenancy enforced automatically.
ppc_creatives	SB ad creatives at ad grain (headline, brand logo, custom images, video asset ids, ASINs, landing page, creative status) plus SD creatives; include_assets=true adds the asset-library inventory.
ppc_new_to_brand	New-to-brand purchases/sales and NTB% per campaign (SB + SD, from standard report columns — no AMC needed). SP has no NTB data.
automation_minmax_results	Recent MinMax budget-analysis runs: scope, top performers, campaigns running hot. NOT the automation approval inbox (that is automation_activity).
automation_aoe_status	Adaptive Optimization Engine: per-campaign configs, modes, guardrails, and recent optimization cycles. NOT the automation approval inbox (automation_activity).
automation_scheduled_tasks	Scheduled tasks: type, cadence, enabled state, last and next run times. NOT the automation approval inbox (that is automation_activity).
keyword_finder	Keyword Finder (reverse-ASIN / multi-input lookup): every keyword phrase the input ASINs are known for, merged from first-party data — SQP (own ASINs, TRUE Amazon search volume), Top Search Terms (ANY marketplace ASIN that is top-3 clicked — works for competitor ASINs), and own ad search terms. Seed `terms` expand to their top clicked ASINs first. Each term carries matched_asins (with per-source evidence), match_count, volume (+volume_source: amazon_sqp = exact; estimated_from_rank = calibrated estimate with volume_band; rank_only = no estimate yet), search_frequency_rank and a relevance_score. Sorted match_count DESC, volume DESC; standard pagination.
brand_sqp	Search Query Performance: organic search funnel per (ASIN, query) — impressions/clicks/cart-adds/purchases with shares. parent_rollup=true aggregates the product family. weeks counts back from the LATEST STORED week (data lags ~2 weeks); rows are newest-week first — page with offset until truncated=false to get the full multi-week window.
brand_top_search_terms	Marketplace-wide top search terms with the top-3 clicked ASINs and their click/conversion shares. WEEK/MONTH rows read the shared full-marketplace store once populated (response carries store=global) — the complete term universe, not just this account's filtered slice.
brand_search_catalog	Per-ASIN search funnel totals across ALL queries (query-less SQP): impressions, clicks, cart adds, purchases, median prices.
brand_repeat_purchase	Customer loyalty per ASIN: repeat buyer share and repeat revenue by week.
brand_market_basket	What customers buy together with each ASIN (bought-with pairs and combination shares).
automation_rules	V2 rule-based automation, READ-ONLY: action=list\|get\|dry_run (mutations live in stage_automation_rule). Every rule has an approval_mode: manual (queue for user approval) \| ai_review (AI approves/rejects, low-confidence escalates) \| ai_shadow (AI analyzes, applies NOTHING) \| auto (applies immediately; can only be set in the app, never from here). list scope=mine (default) shows only the calling user's rules; scope=all_users shows every user's (rows carry owner + owned_by_you). get/dry_run take rule_id; dry_run evaluates the rule without applying anything. describe returns the valid metric/operator/action-type catalog per entity level - ALWAYS check it before building conditions (unknown metrics are rejected at stage time).
stage_automation_rule	Stage a rule mutation: action=create\|update\|delete\|toggle\|duplicate\|assign\|unassign\|run_now. Stages a proposal — NOTHING changes until confirm_staged_changes (reads live in automation_rules). Mutations take rule_id (except create); create/update take params (name, entity_level, conditions, actions, guardrails, run_frequency, approval_mode...). approval_mode accepts manual\|ai_review\|ai_shadow — NEVER auto: granting a rule unsupervised execution is app-only. assign takes params.entities [{entity_type, entity_id}]. Condition metrics/operators/action types, per-action config keys AND top-level rule params are ALL validated (automation_rules action=describe for the catalog) - unknown keys anywhere are rejected with the valid set named. Schedule: run_frequency (daily\|every_n_days\|weekly), run_frequency_n, run_days_of_week (0=Sun..6=Sat), run_hour_utc (0-23). Action configs: add_negative takes negative_type (NEGATIVE_EXACT\|NEGATIVE_PHRASE) + level (auto\|campaign\|ad_group); harvest takes match_type (EXACT\|PHRASE\|BROAD), sub_action, bid, target_campaign_id/target_ad_group_id. Conditions compare a metric to a fixed value, OR to the product family's breakeven ACoS: value_ref='breakeven_acos' + value_offset (points; -5 = fire 5 points below breakeven) instead of value — ACoS metrics only; resolves computed breakeven first, manual BE margin target as fallback. Placement conditions (SP campaign rules): metric keys placement_{tos\|pp\|ros}_{acos\|modifier\|clicks\|spend\|cvr}. run_now executes the rule LIVE after confirmation.
automation_activity	THE approval inbox for V2 rule automation — the ONLY surface for pending automation approvals (MinMax/AOE/scheduled-task tools are separate systems, not this inbox). status=pending (default) means NOT yet approved/dismissed by a user: pending_approval (manual queue + AI escalations), pending_ai_review, shadow (AI Shadow Mode — AI applied NOTHING; needs your approve/dismiss) and ai_rejected (overridable). Rows carry approval_mode (manual\|ai_review\|ai_shadow\|auto), rule owner, needs, undoable, and paginate with total_found/truncated/next_offset. scope=mine (default) shows only the calling user's rules; scope=all_users shows every user's. READ-ONLY: action=list. Approving/rejecting/undoing inbox items lives in stage_automation_review.
stage_automation_review	Stage a decision on automation approval-inbox items (see automation_activity for the inbox itself): action=approve\|reject\|undo, each takes log_ids (max 100) + optional reason, and stages a proposal — NOTHING happens until confirm_staged_changes. approve executes the approved actions LIVE against Amazon after confirmation; undo REVERTS an applied action at Amazon (pushes the prior value back; 24h window; bid/budget/status/placement changes only).
automation_dayparting	Dayparting, READ-ONLY: action=list shows schedules + assignments (mutations live in stage_dayparting_schedule).
stage_dayparting_schedule	Stage a dayparting mutation: action=create\|update\|delete\|toggle\|clone\|assign\|unassign. Stages a proposal — NOTHING changes until confirm_staged_changes (reads live in automation_dayparting). create/update take params (name, hour_matrix 7x24 multiplier grid, schedule_type); assign takes params.entities [{entity_type, entity_id, base_value?}]; mutations take schedule_id.
account_ops_events	Operational health feed (ADMIN-ONLY): deduped errors / warnings / API-throttle events from the worker and web services with occurrence counts, plus failed SP-API sync runs and failed scheduled tasks. Use for "review the ops log" / troubleshooting sweeps. Params: hours (default 168 = 7d), level (error\|warning\|throttle), service (web\|worker), q (search source/message).
account_health_check	Per-connection onboarding + sync health across ALL tenants (SUPER-ADMIN ONLY). Answers "is that new sign-up's data actually flowing?": per core dataset (orders, settlements, MCF shipments, sales & traffic, inventory) the last sync time/status/error and whether it is stale for its cadence, plus a per-connection verdict (ok \| attention \| error), auto-sync state, and whether that user has ever connected an AI client. OPERATIONAL ONLY - carries no revenue, units, margins, ASINs or emails. Params: user_id, seller_connection_id, new_within_days (e.g. 7 to triage just this week's sign-ups).
account_notice_draft	Queue a one-off notice email to a user for admin review (ADMIN-ONLY). Only QUEUES a draft — nothing is emailed until the admin reviews it on the Send Notice screen and clicks Send there. Use after an ops-review finding that warrants proactive user outreach: pass the recipient user_id, a subject, and a plain-text body (blank line = new paragraph; the greeting is added automatically). bell=true also raises an in-app notification when sent.
account_feedback	Feedback & support channel to the AMZ Vault team (NOT an Amazon write): action=submit opens a thread (subject, body, category bug\|idea\|question\|other), action=list shows this account's threads WITH team replies, action=reply (thread_id, body) continues one. Use when the user reports a problem with AMZ Vault itself, is missing data the tools should have, or wants to send the team an idea. Replies from the team appear in the thread (action=list) and on the web at /feedback. To let support view the account, see account_support_access. Email alternative: support@amz-vault.com.
account_support_access	Grant or revoke the AMZ Vault support team's READ-ONLY view of this account: action=grant lets support see what the user sees for 7 days (auto-expires, they can change nothing, and every view notifies the user); action=revoke turns it off immediately. This changes who can access the account, so it ALWAYS needs the user's explicit go-ahead — offer it only when support needs to see a problem first-hand (usually alongside an account_feedback thread).
account_management_guide	The operator's brand & PPC decision framework: margin spine (PPD + margin bands), product postures, campaign structure/bidding, harvesting/negation logic, guardrails and decision triggers. CALL THIS before analyzing an account or proposing ANY optimization (bids, budgets, negatives, harvest, campaigns, pricing) and follow it as the default operating model; pass section= (see toc) for a focused read.
ppc_campaign_create_guide	The verified contract for creating campaigns via stage_campaign_create: per-format required fields, goals, landing-page rules, asset sourcing, safety model, and post-create lifecycle. CALL THIS FIRST whenever the user asks to create an SB campaign.
stage_campaign_create	Create Sponsored Products, Sponsored Brands or Sponsored Display campaigns end-to-end. For SB, call ppc_campaign_create_guide FIRST for the full verified contract. SD item: {name, campaignType: sd_contextual (targets {asins\|categories\|similar_product}) \| sd_audiences (audience {preset: views_similar\|views_advertised, lookback}), budget, defaultBid, skus[], costType cpc\|vcpm, raw_targets?[] for exact expressions} — SD creates default PAUSED for review. SP item: {name, campaignType: auto\|manual_keyword\|manual_product, budget, defaultBid, skus[], keywords?[{text, matchType, bid}], productTargets?[{type, value, bid}], autoTargetingGroups?, negativeKeywords?[], placementTop?/placementProductPage?/placementRestOfSearch?}. SB item: {name, campaignType: sb_product_collection \| sb_video \| sb_store_spotlight, budget, goal? (PAGE_VISIT \| BRAND_IMPRESSION_SHARE \| CONVERSIONS), brandEntityId? (auto-resolved when omitted), keywords?[{text, matchType, bid}]. productCollection: headline (max 50), brandName (max 30), brandLogoAssetId, asins[] (3-5), customImageAssetId?, landingPageType?/landingPageUrl?. video: asins[] (exactly 1), videoAssetId, headline?/brandName?/brandLogoAssetId?. storeSpotlight: headline, brandName, brandLogoAssetId, landingPageUrl (Store URL), subpages[] (exactly 3, each {pageTitle, url, asin}). Asset ids come from ppc_creatives include_assets or an existing SB ad. SB campaigns are created PAUSED for review. Stages a proposal — NOTHING changes until confirm_staged_changes.
ppc_bid_recommendations	Amazon's suggested bid + range per keyword for a SPECIFIC campaign (routed by campaign type). SB: [range_start, range_end], range_start = effective CPC floor. SP: theme-based recommendations for manual keywords AND auto targeting groups (auto_targets: close_match/loose_match/substitutes/complements; needs ad_group_id when the campaign has several ad groups). Check this BEFORE choosing bids. NOT valid for BRAND_IMPRESSION_SHARE/vCPM campaigns — the response carries a warning there (Amazon has no vCPM bid-rec API; use the KEYWORD_INVALID_BID [minBid, maxBid] round-trip instead).
ppc_asset_upload_link	Mint a 1-hour browser-upload link so the USER can hand over a local file (chat attachments cannot reach the server). Flow: call this → send upload_url to the user → they drop the file there (image jpg/png ≤25MB, or video mp4/mov/wmv/avi ≤100MB) → call stage_asset_upload with the returned staged_file_id. Videos over 100MB must be hosted at a public URL instead.
stage_asset_upload	Upload an IMAGE or VIDEO into the Creative Asset Library — from a public source_url, or from a staged_file_id (browser upload via ppc_asset_upload_link; images only). Reference the returned asset_id in stage_campaign_create. brandEntityId auto-resolved for SB use when omitted. VIDEO upload is EXPERIMENTAL: verify the id in an sb_video create afterward. Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_ad_group_create	Create a new SP ad group in an existing campaign (name + default bid; created ENABLED). SB structure goes through stage_campaign_create. Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_ad_group_update	Rename an ad group (SP/SB) or change its default bid (SP only — SB ad groups have no default bid). Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_product_ad_add	Add advertised products to an existing SP or SD ad group (campaign_type, default SP) — created ENABLED. Seller accounts advertise by SKU (give sku; asin alone works only for vendor accounts). Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_campaign_tags	Tag/annotate a campaign in AMZ Vault (add_tags / remove_tags / note) — pure metadata, nothing is sent to Amazon. Tags surface in ppc_campaign_metadata. Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_negatives_remove	REMOVE (archive) negative keywords / negative product targets by their local ids from ppc_negatives — the other half of negation management. Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_portfolio_create	Create a new portfolio (no budget cap; set budgets after via stage_portfolio_update, incl. date-range policies with budget_start_date/budget_end_date). Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_targeting_add	Add keywords, ASIN product targets, and/or category targets to an EXISTING campaign + ad group (SP or SB) — e.g. to act on ppc_harvesting_candidates or extend a live campaign. asin_targets items take exactly one of asin \| category_id \| expression (raw [{type, value}] list for category refinements; SP-only). The destination must be currently ENABLED (campaign and ad group): a PAUSED destination refuses at staging, because targets there sit dormant and re-enabling the campaign would also revive its existing targets — harvest into a live campaign or stage_campaign_create a new one instead. Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_entity_status	Pause/enable/archive specific entities BY ID: ad groups, product ads, keywords, targets, or campaigns (complements the filter-based stage_status_change). ARCHIVED is permanent — Amazon cannot unarchive; confirm intent with the user first. Pausing product ads REQUIRES pause_cause (inventory \| performance) + reason: inventory pauses are watched and a re-enable is staged automatically when stock returns; if the batch would pause a campaign's last active ad, the campaign is paused with it (an ad-less campaign cannot serve and only confuses). Stages a proposal — NOTHING changes until confirm_staged_changes.
ppc_product_report	THE canonical product/family report — ONE call returning every view labeled: family resolution, asin_accurate ad totals (SP+SD ad grain — the numbers to quote for ad spend/ACoS; SB per-ASIN spend is in the blended pnl only), campaign_grain context (top campaigns + family-exclusive placements with modifiers — for finding bleeders, NEVER summed as a product total), blended pnl (TACoS/total sales/margin), and a headline block with quote_rules. PREFER this over assembling the pieces yourself for any "how is product X doing" question.
account_report	THE canonical account overview — ONE call: period cards + settlement waterfall + freshness caveats for the money datasets, with quote_rules. PREFER this for "how is the account doing" questions.
forecast_report	THE 12-month per-ASIN unit forecast (nightly engine): brand totals vs last year, seasonality index, diagnostics incl. trend_check, and per-ASIN rows with the inventory gate (cover days, runout month, LOW STOCK flags). Grounded in stockout-repaired history; recovery is inventory-gated, first month anchors to actual MTD. One currency per call (EUR spans the EU marketplaces). Page rows via offset/next_offset. ALWAYS surface diagnostics.trend_check and quote_rules caveats when quoting numbers. Monthly grain also queryable via data_query dataset 'forecast'.
aplus_document	Fetch ONE A+ content document LIVE, including its full contentModuleList — the copy source for edits (the aplus_content dataset holds metadata only). List keys via data_query 'aplus_content'.
stage_aplus_update	Create or update an A+ (EBC/Premium) content document, optionally attach ASINs and submit for Amazon approval. modules: RAW A+ module JSON (copy shapes from aplus_document) or simplified {type: text \| image_text \| company_logo, headline, body, image}. Images: {staged_file_id: N} via ppc_asset_upload_link — A+ does NOT accept public URLs (bytes ride Amazon's Uploads API on confirm). Omit content_reference_key to CREATE. Draft-only confirms are safe to iterate; submit_for_approval=true sends to Amazon review (asynchronous, typically days). Brand Registry required. Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_listing_update	Update LIVE Amazon listing content: title, bullet_points (full replacement list), description, search_terms (backend keywords, ~249 bytes), and/or price. Single SKU (sku + updates) or items=[{sku, marketplace_id, updates}, ...] (max 25) as ONE staged change. The diff shows current warehouse values before anything is sent; on confirm Amazon PATCHes asynchronously and returns per-SKU status + verbatim issues. Images (W13 P2): main_image + other_images (1-8 gallery slots, in order) — each a public http(s) URL or {staged_file_id: N} from the ppc_asset_upload_link staging flow (Amazon fetches the bytes from AMZ Vault). A+ content comes later. Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_campaign_update	Update campaigns: name, budget_amount, budget_type (LIFETIME is SB-only), bidding_strategy, start_date / end_date (YYYY-MM-DD; null end_date clears it), portfolio_id (null unassigns), bid_optimization (SB-only bool), and/or placement modifiers — works on EXISTING campaigns any time. BATCH: pass campaigns=[{campaign_id, campaign_type, updates}, …] (max 50) to stage MANY campaigns as ONE staged change — one approval to stage, one to confirm. Placements — SP: top_of_search_modifier / product_page_modifier / rest_of_search_modifier; SB: those plus home_modifier. All 0..900%; setting SB placements forces bidOptimization=false (Amazon requires it). SD has no placements. Stages a proposal — NOTHING changes until confirm_staged_changes.
stage_portfolio_update	Update a portfolio: name, budget_amount, budget_policy (DATE_RANGE/MONTHLY_RECURRING/"remove"), budget_start_date, budget_end_date. NOTE: Amazon portfolios cannot be paused/archived — state accepts only ENABLED. To stop a portfolio's spend, cap its budget at $1 with no end date (budget_amount=1, budget_policy=MONTHLY_RECURRING; undo with budget_policy="remove"), or pause its member campaigns (campaign_meta filtered by portfolio_id, then stage_entity_status). Stages a proposal — NOTHING changes until confirm_staged_changes.
ppc_campaigns	Query campaign performance data with optional filters. Returns campaigns sorted by spend (descending) with metrics: cost, sales, ACoS, clicks, impressions, purchases, CTR, CVR, CPC. Supports filtering by ad type (SP/SB/SD), campaign name, and metric thresholds (acos_min, acos_max, spend_min, etc.). IMPORTANT: When the user asks for campaigns above/below a metric threshold, ALWAYS use the appropriate min/max filter parameter — do NOT just sort and return all campaigns.
ppc_search_terms	Query search term performance data. Returns terms sorted by spend with metrics: cost, sales, ACoS, clicks, impressions, purchases, CVR. Supports filtering by search term text, campaign name, and metric thresholds. FULL dataset is reachable: when the response has truncated=true, call again with offset=next_offset until it is false — never treat one page as complete.
ppc_account_summary	Get account-level aggregate metrics for a date range: total spend, sales, ACoS, ROAS, clicks, impressions, purchases.
ppc_daily_trend	Get day-by-day metrics for trend analysis. Returns an array of daily data points with cost, sales, ACoS, clicks, impressions. Useful for spotting spikes, dips, and patterns over time.
ppc_keywords	Query keyword/target bid performance across Sponsored Products AND Sponsored Brands (rows carry ad_type SP/SB; SD targeting expressions live on ppc_query dataset sd_targets). Returns keywords with current bid, cost, sales, ACoS, clicks, and a recommendation hint (increase_bid, decrease_bid, pause_candidate, monitor). Supports metric threshold filters. NOTE: impressions here are AD impressions, not search volume — for organic search-query volume use brand_sqp.
ppc_ad_groups	Query ad group performance data within campaigns. Returns ad groups sorted by spend with metrics: cost, sales, ACoS, clicks, impressions, purchases, CTR, CVR, CPC. Supports filtering by campaign name, campaign ID, ad type, and metric thresholds.
ppc_campaign_details	Get detailed data for specific SP campaigns including placements, advertised ASINs, placement modifiers, and top keywords/targets. GRAIN: advertised_asins is CURRENT ad state (entity-synced; includes never-served ads; source flagged advertised_asins_source), product_ads carries per-ad state, and asins_served_in_window is the report view scoped to the requested range. SP only — SB/SD campaigns come back under notes with the right dataset to query. Use this after ppc_campaigns to drill in.
ppc_campaign_search	Lightweight campaign name lookup. Returns campaign names and IDs only (no metrics). Use this to find campaign IDs before calling other tools.
ppc_advertised_products	Query product/ASIN-level performance (SP+SD ad grain, merged per ASIN with a per-program split; SB per-ASIN spend exists only in the blended P&L). Returns products sorted by spend with status classification (Scaling, Stable, Underperforming, Bleeding). Supports single ASIN, multiple ASINs (for parent family aggregation), or SKU lookup. When multiple ASINs are provided (e.g. all child ASINs from ppc_product_family), also returns family_totals with aggregate metrics across all children.
ppc_product_family	Look up parent/child product hierarchy from the product library (Category Listing report). Use this when the user references a parent SKU, parent ASIN, product family, listing, or any product identifier that isn't a direct campaign name. Returns the parent product info and all child variants with their ASINs. After getting child ASINs, use ppc_advertised_products with the asins parameter to pull PPC performance for the entire family. IMPORTANT: When a user mentions a parent SKU (e.g. 'SEAMLESS-LARGE-SPATULAS'), this is NOT a campaign name — it's a product family identifier. Use this tool first to resolve the child ASINs, then query PPC data for those ASINs.
ppc_placements	Get performance breakdown by placement type (Top of Search, Product Pages, Rest of Search) from SP placement data. Works at ACCOUNT level (default), at CAMPAIGN level (campaign_id / campaign_name_contains), at PRODUCT level (asin/parent_asin/sku — campaigns advertising those products), or per-campaign across the account (group_by_campaign=true). Placement bid modifiers are included in the response (placement_modifiers) when scoped to campaigns.
ppc_budget_alerts	Find campaigns approaching or exceeding their daily budget. Returns campaigns where average daily spend is >= threshold (default 90%) of budget, enriched with Amazon's live budgetUsagePercent snapshot (live_usage_pct, all ad types SP/SB/SD) when available. Full per-day usage history: ppc_query dataset 'budget_usage'.
ppc_conversion_funnel	Get conversion funnel data: Impressions → Clicks → Orders with rates between each stage. Useful for health check analysis.
ppc_change_history	Get recent campaign change history showing what changed, when, old values, and new values. Covers bid, budget, status, and other changes.
ppc_ad_type_breakdown	Get performance comparison across ad types (SP vs SB vs SD). Returns aggregate metrics for each ad type including campaign count.
ppc_match_type_breakdown	Get performance breakdown by keyword match type (Broad, Phrase, Exact, etc.). SP campaigns only. Scope by asin/parent_asin/sku for a true ASIN-accurate cut (SP ad-group grain), or by campaign.
ppc_portfolios	Get portfolio-level performance rollup. Shows each portfolio with campaign count, total spend, sales, and ACoS.
ppc_period_comparison	Compare current period metrics to the previous period of equal length. Returns current metrics, previous metrics, and percentage deltas.
ppc_harvesting_candidates	Find converting search terms eligible for promotion to manual campaigns. Returns terms with conversions at or near target ACoS. Covers SP + SB search terms (rows carry a program label; SD has no search-term report).
ppc_negation_candidates	Find non-converting search terms with significant spend — candidates for negative keyword addition. Returns terms with high clicks/spend but zero orders. Covers SP + SB search terms (rows carry a program label — pass campaign_type=SB to stage_negatives for SB rows).
ppc_dayparting_analytics	Get the dayparting (time-of-day bid modifier) schedule for the profile. Returns a 7x24 grid of bid multipliers by day and hour.
automation_recent_tasks	Get the list of scheduled automation tasks with their status, cadence, and last execution results.
ppc_optimization_suggestions	Analyze campaigns and categorize into top performers (at or below target ACoS), running hot (significantly over target), and wasted spend (spending with no sales). Includes optimization suggestions for each campaign.
stage_bid_changes	Propose bid changes on SP + SB + SD keywords/targets matching filters (ad_type narrows to one program). Pass set_to (exact new bid) OR adjust_pct (percent change) — one is required. PRECISION: target_ids stages exactly those targets (the id every reader returns) — use it whenever a keyword label repeats across ad groups (every AUTO campaign); ad_group_id scopes to one ad group. SAFETY: if the filter matches more than limit, the call is REJECTED (never silently truncated) unless allow_truncation=true; responses always carry matched_count/staged_count/truncated. Prefer adjust_pct for multi-target changes — a flat set_to ignores each target's starting bid. SD current bids are entity-synced ~half-hourly; a NULL current_bid means not yet synced. BIS/vCPM campaigns: check floors via KEYWORD_INVALID_BID semantics — see ppc_bid_recommendations. STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.
stage_budget_changes	Propose SP campaign daily-budget changes. Pass set_to (exact new budget) OR adjust_pct (percent change) — one is required. SB/SD budgets are updated per campaign via stage_campaign_update instead. STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.
stage_status_change	Propose enabling/pausing campaigns matching filters. STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.
stage_negatives	Propose adding negative keywords / negative ASIN targets. Items: campaign_id + keyword_text (SP/SB) or asin_target (SP/SD) or brand_id (SD). Levels: SP campaign or ad_group (pass ad_group_id); SB and SD are AD-GROUP level — ad_group_id required (SB is keyword-only, SD is product/brand-only). match_type: NEGATIVE_EXACT (default) \| NEGATIVE_PHRASE \| NEGATIVE_BROAD — any casing (negativeExact, exact) is accepted and normalized to the correct per-API wire form; SB has no broad. STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.
stage_cogs_update	Propose setting per-SKU landed costs (COGS), time-versioned. Items may also carry optional component costs (factory_cost / freight_cost / duty_cost / packaging_cost) — metadata beside the landed unit_cost, which remains what the P&L uses. STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.
stage_margin_target	Propose a manual BE (breakeven) margin target for a product family (null be_margin_pct clears it so the computed breakeven applies). STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.
stage_competitor_watchlist	Propose adding/removing competitor ASINs on the review-insights watchlist. Watched ASINs get the same weekly review-topic data as own products (readable in the customer_feedback datasets with scope=competitor_asin), fetched by the nightly walk with LEFTOVER call budget - the own catalog always wins. Entries anchor to the product FAMILY: family_asin is one of the user's OWN ASINs (a child resolves to its parent so the whole family shares the list). Cap 10 competitors per family; adds that push the weekly walk over budget WARN but never block (the refresh cycle just stretches past a week). STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.
stage_product_edit	Propose editing one Product Library field (locks it against future syncs). STAGING ONLY: saves a reviewable diff in AMZ Vault — NOTHING is sent to Amazon until confirm_staged_changes is called.
confirm_staged_changes	EXECUTE a pending proposal — call ONLY after you have rendered the full diff to the user as text (entities by name, current → proposed, reason) and they agreed. approved_summary must restate what they approved; it appears in the client's permission prompt, so a bare proposal_id is never shown alone. PARTIAL approval: when the user wants only SOME items, pass the rest as excluded_refs — same behavior as the dashboard's per-item checkboxes. Single-use; expires 60 minutes after propose.
cancel_staged_changes	Cancel a pending proposal without executing it.
staged_changes_pending	List this account's pending (unconfirmed) proposals.
forecast_reorder_report	Reorder advisor for one seller connection: per-ASIN runout dates from the latest forecast (counting FBA + AWD + inbound + open purchase orders), lead-time-aware reorder-by dates, suggested units, and an ADVISORY affordability view of unpaid PO obligations vs the trailing payout pace. Repeat its quote_rules caveats when presenting numbers.
stage_supplier_upsert	Propose creating or updating suppliers (matched by name per connection): contacts, payment terms, and the production/transit lead times that power the reorder advisor. Use this after reading a user's supplier spreadsheet - stage what you parsed and let them confirm. Nothing is saved until the user confirms via confirm_staged_changes - show them the diff first.
stage_po_upsert	Propose creating or updating purchase orders (matched by po_number per connection): supplier_name (created if new), status/milestone dates, ship mode, freight and duty, payments ([{label, amount, due_date, paid}]), notes, and lines ([{sku, units, unit_cost}] - replaces existing lines when provided). QC outcomes belong in notes. Nothing is saved until the user confirms via confirm_staged_changes - show them the diff first.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。