Skip to main content
Glama

Server Details

Analytics, advertising: Facebook/Meta, TikTok, competitor ads. Free plan; Spytrend OAuth in browser

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Server Listing
Spytrend MCP Server
ChatGPT
–
Claude
–

TDQS

A4.1/5.0

Scored across 33 tools

Disambiguation4/5

The surface is large but mostly partitioned cleanly by entity (ads, creatives, advertisers, webmasters, shops, products, influencers, hubs, affiliate offers), and descriptions actively prevent misselection (e.g. find_similar_ads is explicitly entity overlap vs find_similar_creatives visual similarity; search_ads vs get_advertiser for exact counts; search_ads vs get_trends for rankings). The few genuinely confusable pairs remain: get_ad vs get_media (get_ad also returns media), search_ads vs search_creatives on the same underlying ad data, and get_shop's embedded products vs search_products.

Naming Consistency4/5

Nearly everything follows a predictable verb_noun pattern with a small verb vocabulary (search_*, get_*, find_similar_*, list_*, add_to_*), which makes the set scannable. Minor deviations: budget_aggregates is a bare noun phrase with no verb, get_ads_analytics uses a plural noun inconsistent with its siblings, and add_to_favorites vs list_favorites form an asymmetric pair.

Tool Count3/5

33 tools is heavy for any agent to hold in context, and much of that weight is billing/consent/usage plumbing (accept_pricing_terms, estimate_cost, get_usage) repeated conceptually in every description. It is not padding, though: each tool maps to a distinct data vertical or add-on, so the count reflects a genuinely broad platform rather than redundant surface area.

Completeness4/5

Coverage is unusually thorough: search+get pairs for every entity, media delivery, similarity lookups per basis, analytics, trends, budget aggregates, cost estimation, quota, billing consent and favourites persistence. The clearest dead end is favourites management: add_to_favorites and list_favorites exist but there is no remove/delete operation or folder cleanup, so an agent that mis-saves cannot undo it.

Available Tools

33 tools
accept_pricing_termsAccept the MCP pricing termsA
Idempotent
Inspect

Records the account's one-time consent to the current Spytrend MCP pricing (search price × number of filters, ×1 after 500 MCP credits a month). Paid tools refuse with pricing_consent_required until it is given. Call WITHOUT confirm to get the terms text and status; show the terms to the user and call with confirm=true and terms_version ONLY after the user explicitly agrees — never accept on the user's behalf. FREE — does not consume quota.

Inputs: confirm, terms_version. Returns: error, terms, params, accepted, +4 more

add_to_favoritesAdd to favouritesA
Idempotent
Inspect

Save a SELECTION of entities to one of the caller's favourites folders so they can review them later on spytrend.com. entity_type is creo (creatives), webmaster, ad, hub (a hub profile from search_hubs) or shop (a shop domain from search_shops); ids is the list of entity ids from search_ads / search_webmasters / search_creatives / search_hubs / search_shops. For entity_type=hub you MUST also pass hub (the hub slug the ids came from, e.g. 'ecommerce'). folder is OPTIONAL — PREFER a short descriptive name from the user's search (e.g. 'Gambling ads US · Jun 2026'), created automatically if absent; if omitted, a stable dated folder is used. Idempotent — items already in the folder are reported as already_saved, never duplicated or re-charged. BILLING: saving an ad (including multilang) costs 1 MCP credit and saving a creative costs 10 MCP credits; saving does not include another ad media opening; saving a webmaster, a hub profile or a shop is FREE. Already-saved items cost nothing. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: ids (required), entity_type (required), hub, folder. Returns: added, error, failed, folder, +4 more

budget_aggregatesWebsite budget by monthA
Read-only
Inspect

Modelled monthly ad budget of one to three websites over a window of whole months (from_month/to_month YYYY-MM; default: the last six months available). MODEL ESTIMATES in USD (value_kind=modeled_estimate), never observed spend; quote them as estimates. Per site and month (oldest first): p10/p50/p90 band, method_a, method_b, budget_a (sum of the non-skipped countries' budgets), computed_at, ads_new, ads_active, creatives_active, visits; p50_change_pct (vs the previous complete calendar month, 0.1), p50_acceleration_pp (change minus the previous change), ads_new_change_pct, visits_change_pct — null for the first month, the partial current month (partial=true, never used in a change) or a missing/zero base. countries: the top_countries (default 15, max 30) by the latest complete month's budget_a, each with its months (budget_a, budget_share, ads_share, geo_share, geo_source, skipped), budget_share_change_pp and budget_a_change_pct between the last two complete months. creatives per month: creatives counted, allocated_share, top1/top3/top10 shares of the site budget, hhi (sum of squared shares) and the top_creatives (default 10, max 20) with creative_key, share, budget_base, p50, ads, countries. seasonal_multiplier (> 0, <= 10) adds p50_change_adjusted_pct per month and budget_a_change_adjusted_pct per country = round(100 x ((1 + change/100) / multiplier - 1), 1), and echoes seasonal_multiplier. Shares also come as percents: budget_share_pct, top1/top3/top10_share_pct, hhi_pct, share_pct. trend: trailing consecutive declines of p50 and ads_new, last_change_pct, last_acceleration_pp. With 2-3 sites, ranking orders them by last_acceleration_pp, unknown last. A site without a reliable estimate answers status=no_estimate with empty lists (not an error). QUOTA: 1 MCP credit per call. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: domains (required), to_month, from_month, top_countries, +2 more. Returns: data, error, params, addon_hints

estimate_costEstimate the cost of a callA
Read-onlyIdempotent
Inspect

FREE pre-call estimate. Pass the paid tool you are about to call and exactly its arguments; returns max_tokens — the most that call can debit at the account's current balance under the current pricing (filters × monthly step), with the factors used. Call it BEFORE every paid call and tell the user the number. For searches it is an upper bound: only delivered rows are charged, undelivered ones are refunded. For the Startups tools (search_startups, get_startup, enrich_startups, get_startup_ads and the rest) it returns max_objects (Startups objects: 1 per row, 5 per company card) and the subscription's objects_remaining this month instead of MCP credits. Does not run the tool and does not consume quota.

Inputs: tool (required), arguments. Returns: free, note, tool, unit, +16 more

find_competitorsFind competitors of a siteA
Read-only
Inspect

Find the competitors of an advertising site by its domain, across the whole base. competitors are the site's direct competitors, the main list of its competitors page: taken from a saved paid competitor analysis of the site when one exists, otherwise from candidate sites filtered by domain rules and checked one by one by an AI judge. Rows keep that order, strongest first; the row's score field is not a rating here. Each row also carries site_profile, the monthly visits estimate, active_ads (Meta ads active now), product_count, platform, top_country and domain_created. A subdomain is looked up by its registrable domain. competitors_total is the number of rows returned (at most limit). An EMPTY competitors list means the site is not covered yet; it is NOT evidence that the site has no competitors. similar (include_similar=true, the default) are look-alike sites by site profile: they resemble the site but were not checked as rivals, and may include clones, mirrors and other domains of the same brand; similar_total counts every site passing the similarity threshold, not only the returned rows. Use get_shop to open one domain in full and search_ads with landing_domain to list its ads. QUOTA: 1 MCP credit (one entity card). PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: domain (required), limit, include_similar. Returns: error, domain, params, similar, +4 more

find_similar_adsFind related adsA
Read-only
Inspect

Find ads related to one source ad by an explicit overlap basis: fanpage (same Facebook page_id) or domain (same exact landing_domain). This is entity overlap, NOT visual similarity of the material; use find_similar_creatives for that. The source ad is excluded from data, but pagination.total remains the upstream overlap-candidate count before that exclusion; source_excluded and total_semantics make this explicit instead of fabricating an adjusted exact total. Metadata only, cursor-paginated. QUOTA: 1 MCP credit per delivered row (default page 20). PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: ad_id (required), basis (required), limit, cursor. Returns: data, error, params, pagination, +6 more

find_similar_creativesFind creatives that look the sameA
Read-only
Inspect

Find creatives that look the same as one creative, using the production similarity index. This is visual similarity, not exact creative membership. threshold_status distinguishes an explicitly requested threshold from the production default; result_status=bounded_native_cap means the upstream similarity endpoint exposes at most 20 candidates and has_more is conservative at that cap. Returns metadata without media URLs; use get_media for selected ids. QUOTA: 1 MCP credit per delivered row. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: creative_id (required), limit, threshold. Returns: data, error, params, has_more, +6 more

find_similar_webmastersFind similar webmastersA
Read-only
Inspect

Find other webmasters sharing normalized URL-parameter values with a source webmaster. First call get_webmaster_similarity_facets, then pass one returned param_key; optionally narrow to selected values. similarity_basis is url_parameter_overlap and rarity_count shows how many webmasters share the value. Results are deterministically ordered and bounded by the canonical source cap of 5000; result_status/result_cap/total_status state whether that bounded set is complete. QUOTA: 1 MCP credit per delivered row (default page 20). PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: param_key (required), webmaster_id (required), limit, offset, +1 more. Returns: data, error, limit, offset, +9 more

get_adGet ad by id (with media)A
Read-only
Inspect

Fetch a single ad by its id with FULL details including its creative media: the full ad TEXT in body, body_chars (its length in UTF-8 characters), title, creative URL, geos, status, advertiser. body is absent when the ad genuinely has no text; body_chars is absent when the length could not be read — never read an absent field as zero. Media urls on media.spytrend.com may be issued to your account for a limited time — download them promptly rather than storing them, and call get_ad again when a link stops working; a media entry with expiring=true is the original signed Facebook CDN link of a not-yet-mirrored fresh ad — it may die even sooner (re-fetch the ad later for our mirrored link). QUOTA: 50 MCP credits for a multilang-upload ad opening; 1 MCP credit for an ordinary ad. The price includes the available media returned with this card. Each new opening call is charged separately; no subscription to an individual ad is created. A blurred card or a response without usable media is not charged. With source=tiktok: 10 MCP credits per delivered TikTok row. MULTILANG CONTENT: get_ad and get_media(ad) use the same full detail carousel. primary_creative identifies its selected first creative; primary_creative_selection.status describes selected, fallback or unavailable. carousel_position is the original 1-based carousel position, not the returned array index. Missing/unconfirmed selected primary media is not charged or disclosed; both tools report primary_creative_unavailable. Per-slide title/body/link_url describe that slide; when the API omits a slide override, the ad-level value is supplied as its fallback, consistently in both tools. original_landing_domain describes the original ad, while creative_destination_url/domain describe the primary creative's destination. cloaking_detected is a detected domain/copy mismatch, not a verified redirect or a guarantee that a creative is black. Actual per-call debit is reported in _meta.billing.tokens_charged, in Spytrend quota MCP credits (not model tokens); admin may be exempt. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: id (required), source. Returns: data, error, params, source, +2 more

get_ads_analyticsGet ads selection analyticsA
Read-only
Inspect

Get the bounded analytics overview for the current Meta /ads selection: total and display_total plus statuses, countries, AI categories, landing domains, advertisers and webmasters. This is a Pro-or-higher paid surface; every delivered breakdown row costs 1 MCP credit, pending/error responses refund the reservation. The default is 10 rows per section and the absolute maximum is 20; results are flattened in data with a dimension field and include section readiness/truncation metadata. Totals are nullable: null with pending/unavailable status is NOT zero; exact zero is numeric 0 with an exact status. Only the status section removes its own filter; every other section uses the full filtered universe. No pagination, sorting, source, scheduler, force-scrape, TikTok, raw SQL or storage coordinates are accepted. Auto-applied subscription categories are reported in auto_applied_verticals and scope_note. Re-issue the identical call after retry_after_seconds when pending; do not blindly retry paid calls. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: query, saved, dedupe, channel, +45 more. Returns: win, data, tier, error, +24 more

get_advertiserGet advertiser by idA
Read-only
Inspect

Fetch a single advertiser's FULL card by id — the same data as the spytrend.com/advertisers page: name, external_id (FB page id), avatar_url, page_url, total_ads and active_ads (EXACT precomputed counts — THIS is the cheap way to answer 'how many ads / how many are active does this advertiser run', NOT paginating search_ads, whose total is estimated for advertiser_id), launched_14d, top_countries (geo breakdown), platforms, top_landing (destination domains), page_like_count (followers), born (founded date), categories and recent creatives. The card also embeds top_creatives — the advertiser's MOST RE-UPLOADED creatives (a creative's total_ads = how many ads reuse the same material, ordered desc, media stripped/free); present these as the headline at the end and download with get_media (entity_type=creo). The id is an advertiser UUID (from an ad's advertiser_id / get_trends dimension=advertisers) OR a Facebook page id — a fanpage id from get_creative's fanpages, or an ad's page_id: a page id is resolved to its advertiser automatically, so a fanpage you found in a creative resolves straight to its card. A pasted facebook.com page link (any form — vanity name, profile 100…-id, profile.php, Ads Library) is likewise resolved to the page automatically. To list the advertiser's ads, call search_ads with advertiser_id. CATEGORY COUNTERS CONTRACT category_total_ads / subcategory_total_ads and every top_categories[].ads_count / top_subcategories[].ads_count count ONLY the advertiser's AI-LABELED ads - they are a share of the labeled subset, NOT of the page's ad universe. The labeling share is ai_coverage (labeled / total_ads). Read them as: 'N of total_ads ads are labeled (ai_coverage), and X% of THOSE are '. Never compare category_total_ads against total_ads/active_ads directly, and never report a category share as the advertiser's overall vertical mix when ai_coverage is low. QUOTA: 1 MCP credit (one entity card). TOP_CREATIVES CONTRACT each top_creatives entry's total_ads counts the creative's FULL family of matching material across the whole serving universe as the market-wide reuse of that creative; note the family may span MORE advertisers than this page — it is the creative's market-wide reuse, not this advertiser's share. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: id (required). Returns: data, error, params, addon_hints

get_affiliate_celebritiesCelebrities of nutra & crypto affiliate landingsA
Read-only
Inspect

PAID ADD-ONS «Nutra» and «Crypto», sold separately (MCP comes with the annual plan of each vertical). Celebrities that nutra and crypto affiliate landing pages build their pitch on (endorsement, fake news story, interview, quote; plain mentions are not counted) — the same list as the «What's inside» block of the vertical on spytrend.com. Each row: name, role (how the pages present the person), ads (ads of the selection featuring them; an ad with several people counts for each), sites, share of the selection's ads, example_ad_id. Filters: vertical (lp_category), niche (lp_subcategory), Facebook launch date (date_from/date_to), q over name and role; most ads first, limit up to 200, total_celebrities counts every match. To list the ads of a person call search_affiliate_offers with lp_celebrity= and the same vertical. Without the add-on the call is refused; a monthly «site» subscriber is told that MCP access is part of the annual plan. QUOTA: 1 MCP credit per call; summaries are not limited by the section row allowance. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: q, limit, date_to, date_from, +2 more. Returns: data, note, error, scope, +6 more

get_creativeGet creative details and breakdown by idA
Read-only
Inspect

Fetch ONE creative's metadata plus its canonical bounded breakdown by id: activity period/quality, max_days_active with max_days_active_source/max_days_active_quality, delivery_languages with explicit legacy provenance, aggregate counts, advertisers, fanpages, landing domains, webmasters and geos. The ambiguous legacy languages alias is intentionally omitted. When a speech transcript has already been generated for a video, copy_languages is returned separately with copy_language_source=cached_asr_transcript and copy_language_scope=spoken_audio; it describes spoken audio only, not title/body or visual OCR. copy_language_status is available for measured confidence >=0.8, available_low_confidence below that, available_unscored when the provider supplied no probability, and unavailable when there is no valid cached result. This read never starts transcription. Breakdown lists are sorted by ad count desc and capped at 1000 rows; each dimension has its own *_status, _returned and (where a snapshot cardinality exists) _count/_truncated/_count_status. breakdown_status is available_bounded only when every dimension query completed, partial when at least one dimension is unavailable, and unavailable when the breakdown endpoint itself failed. The id is a creative UUID from search_creatives. Media URLs are intentionally excluded; download with get_media (entity_type=creo, same id). Fanpage ids feed the search_creatives fanpages filter and search_ads page_id. QUOTA: 1 MCP credit (one entity card). PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: id (required). Returns: object

get_creative_family_monthly_shareCreative family monthly share year over yearA
Read-only
Inspect

Monthly share of a category's top creative families (ads reusing one exact creative) among the category's ads launched in each complete month per country, beside the same family's share in the same month a year earlier and the change in percentage points; months not available yet come back as null, never 0. QUOTA: 1 MCP credit per call. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: category, to_month, countries, top_families, +1 more. Returns: data, error, params, addon_hints

get_influencerGet influencer cardA
Read-only
Inspect

Fetch one creator card from the influencer directory by platform (youtube or instagram) and slug (as returned by search_influencers). Same fields as a search row plus checked_at (YouTube: when the channel was last re-read), channel_created_at, long_video_count, shorts_count, last_short_at (YouTube) and following, markets (Instagram). CONTACTS, BIOS, VIDEOS AND POSTS ARE NEVER RETURNED — has_email is only a yes/no. Free accounts can open a limited number of cards per day. QUOTA: 1 MCP credit (one entity card). PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: slug (required), platform (required). Returns: url, name, slug, error, +25 more

get_mediaGet creative media (download URLs)A
Read-only
Inspect

Fetch downloadable creative MEDIA (image/video URL + thumbnail) for 1-500 ad or creative UUIDs returned by search_ads / search_creatives. This is the paid delivery step. entity_type is 'ad' or 'creo'. Existing clients keep the {entity_type,items:[{id,media:[{media_type,url,thumbnail_url,fallback_urls}]}]} fields; additive counts, partial and failures explain malformed, quota-limited and unavailable items, plus interrupted items when at least one peer was delivered. Malformed/zero UUIDs never reach the API or consume quota; valid peers in a mixed batch are still processed. duplicate_count reports canonical duplicates, which are fetched and billed once. IMPORTANT: a media URL can become unavailable, so if url returns an HTTP error (e.g. 416/404), retry fallback_urls in order before treating it as unavailable. Typical flow: search_ads (browse metadata, 1 MCP credit per row) → pick ids → get_media. QUOTA: 50 MCP credits per delivered multilang-upload ad, 1 per ordinary ad, 10 per creative-catalogue item (free starter: 500 MCP credits total; paid plans: 40,000/month). The ad price is per returned ad, not per media file. Actual ad membership determines the price even without a preceding filtered search. Every new call is billed; get_ad already includes media, so do not call get_media again for files you already received. Invalid, missing or undelivered items are not charged. Mixed batches examine a quota-bounded prefix and return affordable items with explicit failures for the rest; an unexamined tail may contain affordable ordinary ads, which can be requested separately. get_usage is free. MULTILANG CONTENT: get_ad and get_media(ad) use the same full detail carousel. primary_creative identifies its selected first creative; primary_creative_selection.status describes selected, fallback or unavailable. carousel_position is the original 1-based carousel position, not the returned array index. Missing/unconfirmed selected primary media is not charged or disclosed; both tools report primary_creative_unavailable. Per-slide title/body/link_url describe that slide; when the API omits a slide override, the ad-level value is supplied as its fallback, consistently in both tools. original_landing_domain describes the original ad, while creative_destination_url/domain describe the primary creative's destination. cloaking_detected is a detected domain/copy mismatch, not a verified redirect or a guarantee that a creative is black. Actual per-call debit is reported in _meta.billing.tokens_charged, in Spytrend quota MCP credits (not model tokens); admin may be exempt. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: ids (required), entity_type (required). Returns: error, items, params, partial, +8 more

get_shopGet shop by domainA
Read-only
Inspect

Fetch one domain surface's full profile, with its embedded products paged by products_offset/products_limit (20 by default, at most 50). products_page reports embedded_total, has_more and next_offset; follow it to retrieve every embedded product without losing its fields. products_total counts the product pages of the whole catalog, not embedded_total; use search_products to browse the rest of the catalog. Primary visits is the monthly estimate for traffic_as_of; fetched_at is ingestion time. traffic_sources is typed, while a separate legacy snapshot is kept alongside, and its similarly named traffic fields are not interchangeable with primary visits. the estimate's page title is not a canonical company/brand name; a missing rank on a subdomain is not evidence that the parent domain has no rank. domain_created is the best available registrable-root registration date, not product launch; its per-row RDAP/WHOIS-vs-legacy-fallback provenance is not retained in ClickHouse. ads_monthly/ads_burn use first_parsed_date and mark the open month is_complete=false. fb_signal is correlation_only. The domain/subdomain may be a funnel, runtime, blog or redirect rather than a company/product; inspect registrable_domain and surface_type. Includes AI-ad-category breakdown, recent ads and products. Its active_ads/total_ads count the Meta ads of the WHOLE domain; the product / best-seller list carries no per-product ad counts — call search_products with domain= for per-product numbers. To save it use add_to_favorites (entity_type=shop, ids=[domain]). COUNTS: every count is ONE network over ONE window — never add counts together, never derive a new count, and never present a sum across networks or windows as the domain's total. active_ads / total_ads = Meta (Facebook/Instagram) ads of the whole domain: active now / all time. ads_last_month / ads_prev_month = Meta ads first seen in our data in the last / the previous complete calendar month. ads_active_7d / ads_active_14d / ads_active_28d = Meta ads that were active 7 / 14 / 28 days ago; launches_7d / launches_28d = Meta ad launches counted for the shop over the last 7 / 28 days. google_ads / google_ads_active = Google ads: all published / active now. tt_ads / tt_ads_30d = TikTok ads: all time / active in the last 30 days. The Google and TikTok fields are omitted when no ads of that network were found for the domain. ads_geo[] is per targeted country: ads = Meta ads targeting that country, share = that count over an internal row count of the domain (not total_ads); one ad targets several countries, so ads_geo rows overlap and shares do not add up to 1 — never divide ads by share, never add ads_geo rows, ads_monthly or ads_burn months into a total: the all-time Meta total is total_ads. To describe ads across networks, name each network with its own number and window. Product counts are different fields — product_count is the shop's catalog: the number of UNIQUE products, where several product pages (URLs/handles) of one product, such as a -1 copy or a funnel duplicate, count once (merged by brand and title); only when our product data is smaller than the site crawler's counter is product_count that crawler counter. products_unique = unique products in our data, products_total = product pages (URLs) of the shop in our data, duplicates of one product included, catalog_size_true = catalog size from the sitemap (0 = unknown): call product_count the catalog and quote any other field by its meaning; products is a SAMPLE of the catalog's pages (best-sellers first) — its length is not a product count. A number with no field here is not available: say it is not available instead of computing it. QUOTA: 1 MCP credit (one entity card). PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: domain (required), products_limit, products_offset. Returns: data, error, params, addon_hints

get_usageGet usage / quotaA
Read-onlyIdempotent
Inspect

Return the caller's current MCP quota: plan, MCP credits used, remaining and limit (free starter = 500 MCP credits total forever; paid plans = 40,000/month ≈ 2,000 default-page searches; Enterprise = personal limit via support). MCP credit costs: 1 per delivered result (an ad/webmaster/advertiser row, a trends row, an entity card), ordinary ad media = 1, multilang-upload ad opening = 50, creative media = 10, TikTok row = 10. Each opening call is billed separately. You pay only for results actually delivered (short pages auto-refund). This call is FREE — it consumes no quota.

Returns: note, plan, used, error, +11 more

get_web2app_marketWeb2App market summaryA
Read-only
Inspect

PAID ADD-ON «Web2App» (MCP comes with the annual plan). Summary of the web2app (quiz-to-paywall) advertising market from the Spytrend ad base: ads by brand, category, domain, page, country, language or month, with month range and filters. Without the add-on the call is refused; a monthly «site» subscriber is told that MCP access is part of the annual plan. QUOTA: 1 MCP credit per call (nothing for an account with a personal Web2App limit); summaries are not limited by the section row allowance. PAYWALL PRICES: every row of a brand, category, domain or page breakdown carries paywall — the prices of that row's funnels in the Spytrend Web2App library: funnels (walked funnels), priced_funnels, trial_funnels, currency, price_min / price_max / price_median (the plans in that currency), and latest — up to 3 latest priced funnels (funnel_id, host, geo, walked_at) with their plans (name, price, currency, period, intro_price, intro_period, full_price, trial_days, renewal_price, renewal_period, badge) or, when the plans were not parsed, screen_prices as written on the paywall screen. A row without paywall has no walked funnel yet. The prices are of the funnels, not limited by the month range. Quiz screens and screenshots are not in this answer: every row carries funnels_url — the funnels of that brand / category / domain / page / language in the Spytrend library, which the account owner opens on the site to view and download them. DATA: this is the Spytrend Web2App library. walked_at is the date the funnel's screens were captured; the country is only what geo says (empty geo = unknown, do not assume one); the funnel's length is steps_total / the screens returned — do not estimate them. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: q, to, geo, from, +4 more. Returns: object

get_webmasterGet webmaster by idA
Read-only
Inspect

Fetch a single webmaster (affiliate NETWORK) by UUID: aggregate stats PLUS top_creatives — the creatives this webmaster re-uploads the MOST, ordered by the webmaster's OWN in-slice ad count (slice.ads_in_slice desc — the deliberate slice order, matching what the profile page shows), media stripped/free. Each entry's total_ads is the creative's market-wide family size, folded best-effort from family redirects and floored at ads_in_slice — total_ads == ads_in_slice therefore often means 'family cards not yet built', not 'this webmaster owns the whole market'; it is context, not the sort key. analytics_pending=true means the canonical PostgreSQL identity exists but its ClickHouse aggregate is not published yet, so zero counters are not analytical zeroes. fanpages_status explicitly reports advertiser-aligned lifecycle enrichment as available, partial, unavailable or not_applicable; an omitted fanpages array is therefore never evidence that a page is alive. The id MUST be the canonical UUID returned by search_webmasters; domain names and display names are rejected instead of silently widening to the whole database. Present top_creatives as the headline final step; for the rest of the network use search_creatives?webmaster_id / search_ads?webmaster_id, and download media with get_media (entity_type=creo). identifier_inventory_semantics explains why historical page/domain/pixel inventory counts are not comparable to total_ads. attribution_link_stats.merge_edges answers WHY these identifiers sit in one network: each entry is a {page_id, page_name, domain, ads} pair — that fanpage ran exactly that many ads on that landing domain, and such a pair is what merges two networks into one (an ad whose domain belongs to network A and whose fanpage belongs to network B fuses them permanently). Weigh the edges before claiming a single operator: a 1-3 ad edge next to 100+ ad edges is a thin bridge, typically a catalog/feed ad, and is weak evidence of shared ownership; identifiers with no edge at all are inherited from earlier merges and prove nothing today. QUOTA: 1 MCP credit (one entity card). TIKTOK: with source=tiktok this fetches the TikTok cluster card instead (business-id rollup, same UUID space as search_webmasters source=tiktok results) — ⚠️ costs 10 MCP credits and requires a Pro-or-higher plan; the Meta-only embeds (top_creatives, attribution link-stats) are omitted on the TikTok card. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: id (required), source, date_to, countries, +1 more. Returns: data, error, params, addon_hints

get_webmaster_similarity_facetsGet webmaster similarity facetsA
Read-onlyIdempotent
Inspect

List the URL-parameter keys and normalized values that can be used to find related webmasters. Similarity here means shared affiliate/tracking parameter values, not name or domain similarity. Returns only facets that have at least one other webmaster match. FREE.

Inputs: webmaster_id (required). Returns: data, error, params, addon_hints, +2 more

list_favoritesList favouritesA
Read-onlyIdempotent
Inspect

List the caller's favourites folders (name, entity_type, item_count). Pass entity_type (creo/webmaster/ad/hub/shop) to filter; omit it to list folders across all types. Pass folder (a folder name) to instead return the ITEMS inside that folder: entity ids for creo/webmaster/ad (usable with get_creative / get_webmaster / get_ad), resolved hub profiles (hub + id + label) for hub folders, and domains for shop folders. Use this to confirm what add_to_favorites saved and to read a folder back. FREE — does not consume quota.

Inputs: folder, entity_type. Returns: error, params, folders, addon_hints, +1 more

search_adsSearch adsA
Read-only
Inspect

Search the spytrend.com ad database and return ad METADATA: title, body_chars (the LENGTH of the ad text in UTF-8 characters), landing domain, status, geos, activity, advertiser, ai_enrichment (ai_category/media_type), media_count and creative-format metadata. The ad TEXT ITSELF is deliberately NOT in list rows — an average body is ~1.1k characters and would bloat a 20-row page 20-80x; fetch the text for a specific ad with get_ad, and use body_chars plus min_body_chars/max_body_chars to find the ads worth opening. The visible /ads Format filter targets creative_formats (video/carousel/single/dynamic); publisher placements are filtered separately via platforms. The downloadable creative media is NOT included here — fetch it with get_media using the returned ids. Filters: keyword (query), country/countries (multi-geo), platforms, categories (ai_category slug), ai_subcategory, status_today (active/inactive/vanished), advertiser_id, webmaster_id, landing_domain, media_type; languages, formats (creative_formats: video/carousel/single/dynamic), cta_buttons, domain_zones, search_in (which field query matches: all/title/advertiser/text), platforms_mode (platforms any/all); point lookups pixel_id / page_id / resolved_ip and contains_in_links (tracking fragments like pixel_id=/sub1=/utm); ranges min_days_active/days_active_to, min_page_likes/max_page_likes, min_body_chars/max_body_chars (ad-text length in characters; both directions cover only ads with known non-empty text), date_from/date_to (Facebook launch date — THE axis for 'new ads in a window': new = launched on Facebook then; first_seen_from/to is the date we first indexed the ad, which also catches late-indexed OLD ads — never use it for market newness); max_countries (with selected countries: additional GEOs outside them; without selected GEO: total GEOs), dedupe (unique creatives only), and saved/folder scopes (saved=all, folder_id). Sort with sort_by + sort_order. Use sort_by=most_reused_creative to rank the selected results by how many ads share the same creative; rows include same_creative_ads_in_selection and other_ads_with_same_creative for the selected filters, plus same_creative_ads_lifetime and advertisers_using_same_creative for the lifetime catalog. creative_match_type=exact identifies the matching contract and creative_reuse_status=exact|unavailable qualifies the counts. For most_reused_creative the absolute number of distinct creative groups is intentionally unavailable/null; page with has_more and next_cursor instead of retrying for a total. To find ads on a domain use landing_domain — NOT query. Meta pages contain at most 20 complete rows; follow next_cursor to retrieve more, even if a legacy caller requests limit=200. Cursor pagination via next_cursor; pagination always includes total and total_status (exact/estimated/unavailable), plus counted_at/count_cached for exact analytical totals. Any closed launch OR discovery window of at most 31 calendar days completes a raw exact unique-ad count in-call. A discovery request with exactly one country plus optional AI category/subcategory filters can instead use the canonical daily cube for an exact count across up to 90 inclusive days, or from first_seen_from through today; no other filters may be present on that cube path. Other wider/open combinations use the normal estimated/unavailable contract, and malformed/reversed dates are rejected. An exact count that includes today is exact for ads ingested so far, while analysis.includes_open_utc_day and data_complete_through make the incomplete tail explicit. status_today always means CURRENT state: with a date window, active is the currently-active survivors of that selected cohort, not historical activity on each date. Except for the intentional most_reused_creative group-total omission described above, unavailable means the async count did not settle inside this call: the number is PENDING, not zero and not a measurement; re-issue the identical call in a few seconds to obtain it (analysis.count_note repeats this warning in-band). NEVER present an unavailable count as 0. With categories set, matches and totals cover AI-LABELED ads only — a labeled SUBSET of the market (analysis.category_semantics=ai_labeled_ads_only_not_comparable_to_extrapolated_trends); get_trends aggregates for the same category×geo are extrapolated market estimates and will always be larger — never cross-compare the two. For an advertiser's or webmaster's EXACT ad count (total AND active), do NOT paginate search_ads — call get_advertiser / get_webmaster. To download the creatives, pass the ids to get_media; to SAVE them, pass the ids to add_to_favorites. Respects the caller's plan/verticals. For aggregate rankings use get_trends. MULTILANG UPLOAD: formats=[carousel_multilang] selects the same detected carousel pattern as the website; carousel_multilang_categorized selects its AI-categorized subset. This is independent of the languages filter. Formats combine with OR, so do not combine the base and categorized variants when requesting only categorized results. Search remains 1 MCP credit per row; opening a matching ad with get_ad or get_media costs 50 MCP credits. EU transparency: ads delivered in the EU carry a disclosure with eu_total_reach (accounts reached inside the EU over the ad's lifetime — reach, not impressions or spend), the countries it was delivered in, audience gender/age and the payer. Filter on it with eu_only, eu_countries (+ eu_countries_match), eu_reach_min/max, eu_gender, eu_age_min/max and eu_payer; every result row then carries an eu_transparency block, and get_ad adds the country × age × gender breakdown. Meta source only. QUOTA: 1 MCP credit per DELIVERED result (default page 20 = 20 MCP credits; short pages auto-refund). Results carry metadata only; get_ad/get_media charge 50 MCP credits per multilang-upload ad opening, 1 per ordinary ad, and get_media charges 10 per creative-catalogue item. Each new opening call is billed separately. Meta search_ads rows include is_multilang and opening_price (Spytrend MCP credits per ad per call); unavailable/null means the price could not be verified, not zero. is_multilang=true marks a multi-language upload («залив языками»): a masked carousel where some slides are decoys for ad review; where the real (black) slide is found it is the one shown first and used for grouping. multilang_black_missing=true means the real slide is not found yet: the media shown is a decoy and must not be treated as the creative. Opening quotes are not a debit or a price lock. Request small limits and narrow filters. TIKTOK SOURCE: pass source="tiktok" to query the TIKTOK ad corpus instead of Meta. (The platforms filter does NOT do this — platforms are Meta publisher placements.) ⚠️ TIKTOK IS PAID PER ROW at a premium: every DELIVERED TikTok ad row costs 10 MCP credits and every TikTok webmaster row/card costs 10 MCP credits (Meta rows cost 1), deducted from the same MCP credit balance (paid plans: 40,000/month = up to 400 TikTok rows). Request small limits and narrow filters; you are charged only for rows actually delivered (short pages auto-refund; if the balance covers only part of the request, that part is delivered — a 3-row request on a 15-MCP credit balance returns 1 row and charges 10). TikTok requires a Pro-or-higher plan: free/starter callers and unlinked agents get an actionable upgrade refusal, never data and never a charge. TikTok rows have their OWN shape, returned under tiktok_data (verified live 2026-07-30): id/external_id (TikTok ad id), advertiser{id,external_id,name} plus advertiser_id (TikTok BUSINESS id), start_date/end_date (the ad's delivery window) and first_seen_date/last_seen_date (Spytrend indexing), days_active, is_active + status_today, ai_category/ai_subcategory, countries + targeting_geos + targeting_details (OS/age/gender/regions), audience_size, objective, sponsor (the 'paid for by' funder) and registry_location, landing_domain + link_url, body/title/call_to_action, creative_format, creative_id, creative_ad_count (how many ads reuse that creative), is_blurred/is_cloaked, and media[] with media_type + thumbnail_url on media-tt.spytrend.com. Media comes WITH the row — do NOT call get_media for TikTok ids (it serves Meta entities only). There are no TikTok engagement counters (plays/likes/comments/shares) on this surface. The TikTok feed serves the ARCHIVED TikTok corpus — exactly what the spytrend.com /ads TikTok tab shows — and pagination carries has_more/next_cursor plus total with total_status (exact, estimated or unavailable; unavailable is not zero). With source=tiktok: Supported TikTok filters: query/search_in, country/countries, country_match, categories, ai_subcategory, languages, formats (single|carousel|video), landing_domain, landing_domain_exact, advertiser_id (TikTok business id), webmaster_id, contains_in_links, media_type, cta_buttons, domain_zones, status_today (active|inactive), min_days_active/days_active_to, max_countries, dedupe, date_from/date_to (delivery-window overlap), sort_by=date|days_active, sort_order, limit, cursor. landing_domain includes the normalized host and its subdomains by default; landing_domain_exact=true restricts it to that host. Exact-host matches are current; subdomain coverage comes from an archival index whose build date and limitations are returned in meta.subdomain_index. When the subdomain index budget is exceeded, only exact-host matches are returned with meta.subdomain_index.mode=exact_only; use landing_domain_exact=true for exact-host lookup directly. Countries overrides country. Categories and ai_subcategory combine with OR on TikTok. title and text both search the ad text; advertiser searches the advertiser name. date_from/date_to selects ads whose delivery window overlaps the requested inclusive period, not ads launched in that period. Active means shown within the last 3 calendar days. Unsupported filters (including hub_domains, folder_id and saved) are REJECTED before charging; no filter is silently ignored. Default TikTok limit is 10; each delivered row costs 10 MCP credits. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: limit, query, saved, cursor, +51 more. Returns: data, meta, error, params, +6 more

search_advertisersSearch advertisersA
Read-only
Inspect

Search advertisers by NAME, numeric Facebook page id, or a pasted facebook.com page link (typeahead; query ≥2 chars). A link in any form (vanity name, profile 100…-id, profile.php, Ads Library view_all_page_id) and either id namespace resolve to the canonical fanpage with the exact match first. Returns advertisers with external_id (the Facebook page id), advertiser_id (the INTERNAL advertiser UUID; advertiser_ids lists every internal record when a page has several) and ad_count. To fetch ONE advertiser's full card by id use get_advertiser; to see an advertiser's ads, call search_ads with page_id=<external_id> (covers every internal record of the page) or advertiser_id=<advertiser_id>. For advertiser RANKINGS, ordering and filters (category/country/followers/founded-date/life_status/hubs), use get_trends with dimension=advertisers. With search_arbitrage=true or any sa_* filter it lists the advertisers whose ads are search arbitrage (ads leading to pages that earn from search-ads clicks), most ads first. FREE PLAN COUNTS: when the plan's archive window narrows a request, pagination.total_status is "restricted" and meta.plan_window_cutoff names the boundary — the count then describes the window actually searched, NOT the one requested, so a zero means "nothing in the archive window" and never "nothing exists". QUOTA: 1 MCP credit per DELIVERED result from your plan balance (free starter: 500 MCP credits lifetime; paid plans: 40,000/month; short pages auto-refund — you pay only for results you receive). Default page is 20 results = 20 MCP credits; pass limit (1–200) to size it. get_usage is free. Autonomous agents must be linked to a spytrend account to access data — an unlinked agent gets an actionable connect-your-account refusal (create agent credentials at spytrend.com/settings?tab=ai, or a human claims it by client_id), NOT a server error. Calls are rate-limited per authenticated user (deployment defaults: 60/minute and 1000/hour); a rate-limit refusal is an MCP tool error with structured error.code=rate_limit_exceeded, scope, window and retry_after_seconds. CONCURRENCY: heavy analytical calls (get_trends, search_ads, search_creatives) are admitted ONE AT A TIME per account — fanning out 5-10 of them in parallel does not go faster, it returns admission refusals for all but one. Issue heavy calls sequentially; light lookups (get_ad, get_advertiser, get_usage) are not gated. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: limit, query. Returns: meta, error, items, total, +2 more

search_affiliate_offersSearch nutra & crypto affiliate offersA
Read-only
Inspect

PAID ADD-ONS «Nutra» and «Crypto», sold separately (MCP comes with the annual plan of each vertical). Find Meta ads whose landing pages are nutra or crypto affiliate offers, filtered by vertical (lp_category), niche (lp_subcategory), offer (lp_product), celebrity the landing page features (lp_celebrity — names as returned by get_affiliate_celebrities), text (q) and Facebook launch date (date_from/date_to). PAGING: one call returns at most 50 rows; when has_more=true, repeat the call with the same filters and cursor=next_cursor to get the next page (new rows, never the same ones) — keep following next_cursor until has_more=false. total is the exact number of matching ads and is omitted when no exact count is available (absent total never means zero). Each row: ad_id, advertiser, landing_domain, vertical, niche, offer. Without the add-on the call is refused; a monthly «site» subscriber is told that MCP access is part of the annual plan. QUOTA: 1 MCP credit per delivered row; section rows have their own allowance — up to 500 rows per UTC day and 5 000 per UTC month per account, shared by every tool (search_ads, get_ad, get_media and the rest count the Nutra / Crypto / Web2App rows they return too), which MCP credit packs do not raise; market summaries (get_web2app_market) are outside it. PRICING: on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: q, limit, cursor, date_to, +5 more. Returns: data, error, total, params, +5 more

search_contentSearch content ideas (Content AI)A
Read-only
Inspect

Content AI (lite) search: find short-video content ideas by meaning — Instagram Reels, TikTok and YouTube Shorts ranked for a free-text query (a topic, a niche, a hook, an idea, up to 500 characters; any language). One row = one video. Rows carry id, platform, views, likes, comments, shares (null when the platform hides it), viral_score, published_at, language and duration_sec. AUTHORS, CAPTIONS, TITLES AND LINKS ARE NOT RETURNED — Content AI masks them by design; never invent them, and send the user to Content AI on spytrend.com for the full cards. Filters: platforms (instagram, tiktok, youtube — a list; empty = all), published_within_days (7, 30 or 90 — only videos published in that window), sort (best_match default, fire, views, likes, comments, newest). The tool returns the FIRST page only (limit at most 10): there is no paging, repeat the search with a sharper query instead. total is the number of matches found so far for the query (not an exact market size) and can be absent; low_relevance=true means nothing matched well — say so instead of presenting weak rows as ideas. filters_applied=false means this deployment ignored sort, platforms and published_within_days for this call — do not claim the result was filtered by them. Each search also counts against the account's daily Content AI search limit; a repeated identical query is served from cache. Gate errors are reported as tool errors: subscription_required (Content AI needs a subscription or token balance on the account), not available, or busy (retry after the indicated delay). QUOTA: 1 MCP credit per delivered row; short pages are refunded. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: query (required), sort, limit, platforms, +1 more. Returns: data, note, error, total, +5 more

search_creativesSearch creativesA
Read-only
Inspect

Browse and filter Meta creative families (source=meta only; TikTok callers must use search_ads with source=tiktok and dedupe=true) and return metadata only. Filters include country/countries, exclude_countries, categories, ai_subcategory, media_type/media_types, domain_zone, advertiser_id/advertiser_ids, webmaster_id, fanpages, hub_domains/channel, active_ads_today_from, last_seen_from/to, period_from/to, max_countries, min_geo_share, folder_id and saved=all. last_seen_from/to is creative activity eligibility; period_from/to (date_from/to aliases) is the independent in-period window for ads_in_period — the window itself does NOT filter rows (total and rows stay the same); add ads_in_period_from=N to keep only creatives with at least N ads in it (not yet with country/countries). The applied window is echoed in meta.period_window. Sort by relevance, total_ads, ads_in_period/reuploads, active_ads, last_seen or fb_created. With an advertiser/webmaster slice, pagination.sort_semantics=slice_ordered_by_webmaster|slice_ordered_by_advertiser and slice.ads_in_slice is the ordering key. total_ads remains the lifetime whole-family count; ads_in_period is the count for the selected period on the backend-reported date axis. Always read pagination.period_axis: first_seen means first discovery by Spytrend; facebook_start_date means launch on Facebook after the verified launch-generation cutover. query/search_in searches the texts of the creative family's ads; all query words must match the family. Cursor-paginated. Download with get_media and save with add_to_favorites. DATA COVERAGE: pagination.total_status is exact, estimated or unavailable, and for free plans restricted; when the requested dates (or the newest-first order, or an open-ended date range) reach past the day every creative is complete through (meta.data_through) it is partial (some creatives have those days, the rest do not yet) or stale (no creative reaches the requested days). meta.served_through is the newest day any creative reaches (absent when it could not be read; the verdict is then never stale) and meta.coverage_note repeats both. A stale or partial zero or short page means there is no data for those days yet, never that no creatives exist, so say the data is complete through meta.data_through and partly available up to meta.served_through. QUOTA: 1 MCP credit per DELIVERED result (default page 20 = 20 MCP credits; short pages auto-refund). Results carry metadata only; get_ad/get_media charge 50 MCP credits per multilang-upload ad opening, 1 per ordinary ad, and get_media charges 10 per creative-catalogue item. Each new opening call is billed separately. Meta search_ads rows include is_multilang and opening_price (Spytrend MCP credits per ad per call); unavailable/null means the price could not be verified, not zero. is_multilang=true marks a multi-language upload («залив языками»): a masked carousel where some slides are decoys for ad review; where the real (black) slide is found it is the one shown first and used for grouping. multilang_black_missing=true means the real slide is not found yet: the media shown is a decoy and must not be treated as the creative. Opening quotes are not a debit or a price lock. Request small limits and narrow filters. PERIOD PARITY CONTRACT: the /creo web filters ai_subcategory, hub_domains[] and active_ads_today_from are available here too. last_seen_from/to filters the creative's LAST recorded activity and does not change count semantics. period_from/period_to is the independent inclusive window used for ads_in_period; date_from/date_to are compatibility aliases of it and, unlike search_ads.date_from, do not filter rows — ads_in_period_from does. A closed explicit period enables ads_in_period automatically. sort_by=ads_in_period or reuploads ranks by that measured in-period count, while total_ads remains lifetime family reuse. The legacy period_metric=ad_debuts plus closed last_seen bounds remains accepted temporarily. Empty pages do not fabricate a count. Invalid/open/reversed periods are rejected before quota or upstream work, and a backend response missing ads_in_period is rejected rather than presented as zero. AXIS CONTRACT: read pagination.period_axis on every period response. "first_seen" means the ad was first discovered by Spytrend; "facebook_start_date" means the ad was launched on Facebook, and is emitted only after the verified launch-generation cutover. Never assume an axis from the request or description. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: limit, query, saved, cursor, +31 more. Returns: data, meta, error, params, +2 more

search_hubsSearch hubs (destinations)A
Read-only
Inspect

Explore HUBS — where ads send traffic, grouped by destination (Social Media: Facebook/Instagram/Telegram/WhatsApp; App Stores; Amazon; E-commerce; Popular; Platforms). Call WITHOUT hub to get the catalog (the list of hub slugs + labels) — that is FREE. Call WITH hub set to a slug to drill into that hub's destination profiles, filtered by query (free-text profile name/id search), ai_category, min_total/min_active/min_sticky ads, date_from/date_to, window (7d/30d/90d; NOTE: lifetime counters on the default snapshot path — window is a no-op there, prefer date_from/date_to or sort=active_desc for recency), country (ISO alpha-2 — keep only profiles with ads in that geo) and exclude_cloaking (drop multi-geo redirect/cloaking domains), ordered by sort (ad_count_desc default = LIFETIME volume, ad_count_asc, last_seen_desc, sticky_desc, sticky_asc, active_desc/active_asc = CURRENTLY-active 'hot now', or relevance = ad volume IN the selected country — needs country). For a per-geo ranking of real storefronts (e.g. top e-commerce in BR), combine country + sort=relevance + exclude_cloaking. The catalog call (no hub) is FREE; profile rows cost 1 MCP credit each. FREE PLAN COUNTS: when the plan's archive window narrows a request, pagination.total_status is "restricted" and meta.plan_window_cutoff names the boundary — the count then describes the window actually searched, NOT the one requested, so a zero means "nothing in the archive window" and never "nothing exists". QUOTA: 1 MCP credit per DELIVERED result from your plan balance (free starter: 500 MCP credits lifetime; paid plans: 40,000/month; short pages auto-refund — you pay only for results you receive). Default page is 20 results = 20 MCP credits; pass limit (1–200) to size it. get_usage is free. Autonomous agents must be linked to a spytrend account to access data — an unlinked agent gets an actionable connect-your-account refusal (create agent credentials at spytrend.com/settings?tab=ai, or a human claims it by client_id), NOT a server error. Calls are rate-limited per authenticated user (deployment defaults: 60/minute and 1000/hour); a rate-limit refusal is an MCP tool error with structured error.code=rate_limit_exceeded, scope, window and retry_after_seconds. CONCURRENCY: heavy analytical calls (get_trends, search_ads, search_creatives) are admitted ONE AT A TIME per account — fanning out 5-10 of them in parallel does not go faster, it returns admission refusals for all but one. Issue heavy calls sequentially; light lookups (get_ad, get_advertiser, get_usage) are not gated. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: hub, sort, limit, query, +9 more. Returns: data, meta, error, params, +2 more

search_influencersSearch influencersA
Read-only
Inspect

Search the INFLUENCER directory (the website's /influence page): YouTube channels and Instagram accounts with audience size and activity. One row = one creator. platform is required: youtube or instagram. Filters: q (name / topic words), country (ISO-2 code such as US, or the English country name as the directory writes it, comma separated), category and niche (YouTube only; the directory's own labels, exact match, comma separated — YouTube category examples: Gaming, Music, Education, Comedy, Sports, 'Beauty & Makeup', 'Tech, AI & Software', 'Finance & Cryptocurrency', 'Food, Drink & Cooking', Fitness, 'Travel & Events'; when unsure of a label search by q instead), followers_min / followers_max (subscribers / followers), last_video_days (creators active in the last N days: last video on YouTube, last post on Instagram), has_email (true = creators with an email in the directory), sort (YouTube: followers default, views, videos, last_video; Instagram: followers only). Instagram rows carry the account handle in username and have no niche, avg_views or lang_hint. Rows: slug, name, platform, followers, avg_views (YouTube: average views per video), count_views (YouTube: total views), media_count (videos / posts), country, niche, category, lang_hint (YouTube writing-script hint such as 'latin' — NOT a language), last_video_at / last_post_at, has_email, url (YouTube creator page on spytrend.com). CONTACTS ARE NEVER RETURNED: no emails, phones, websites, social links or bios — has_email is only a yes/no. total_estimate is an ESTIMATE scaled to the directory size, never an exact count. Pagination: limit is at most 10; offset must be a multiple of limit. Callers without an Influence subscription get subscription_locked=true: only the first row carries statistics, the others are name/country/niche teasers (stats_hidden=true, not charged) and there is no second page. QUOTA: 1 MCP credit per row that carries statistics; teaser rows and short pages are refunded. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: platform (required), q, sort, limit, +8 more. Returns: data, note, error, offset, +9 more

search_productsSearch advertised productsA
Read-only
Inspect

Search e-commerce PRODUCTS that ads lead to — the data behind the website's /shops/products page. One row = ONE product page (domain/products/handle) of ONE shop, with that product's OWN ad counters: ads = ads leading to this product among the ads Spytrend first saw in the last 180 days; ads_active = how many of them were ACTIVE on active_as_of — the day of the daily data snapshot the counters are taken on, returned with the result (say 'active on 04.10', never 'active now'); creatives, reuploads and geos; days_in_ads = days from the product's first launch to today (if something is active) or to its last launch; fb_launch_date / last_launch_date = first and last Facebook launch of the product's ads (YYYY-MM-DD); win_badge = testing (active, under 14 days in ads) | heating (active, 14-29 days) | proven (active, 30+ days and 10+ ads) | ran30 (30+ days, not proven); no badge = not active and under 30 days. price/currency come from the shop catalog (0 = no catalog). shop = the store (domain, platform, top_country, monthly visits estimate, categories). product_url is the product page on spytrend.com (link it); ads_url lists the product's ads. COUNTS ARE PER PRODUCT: never use a shop's active_ads/total_ads from search_shops/get_shop as a product's numbers — they count the WHOLE domain. Filters: q = substring of the product handle, i.e. the URL slug (lower-case words joined by dashes: 'weighted blanket' matches weighted-blanket-queen) — NOT the product title: a product sold as 'CloudAlign Pillow' may live at cloud-alignment-pillow, so when a named product is missing from the rows, retry with a shorter fragment or the compound word split by a dash ('cloudalign' -> 'cloud-align'), or domain= when the shop is known; country = ISO-2 codes (comma separated) of the SHOP's main visitor country, not of the ads — never present it as the country the ads run in; ai_category = Spytrend AD category slugs (comma separated); site_category = estimated site category slug; platform = commerce platform of the shop (comma separated, e.g. Shopify); domain = exact shop domains (comma separated) — use it for 'products of this shop'; active_only=true = only products with an ad active on active_as_of; win_badge = comma separated badges; date_from/date_to (YYYY-MM-DD) = window of Facebook launches ('launched/advertised during a period'): a product matches when one of its ads launched inside the window, and ads_in_period is the number of such launches — this includes old products that relaunched an ad in the window. first_seen_days (1-365) = only products whose FIRST Facebook launch (fb_launch_date) happened in the last N days: for 'first seen / new products / started advertising in the last N days and still active' pass first_seen_days=N + active_only=true — the tool sets the same boundary as the website's 'last N days' preset (today minus N days; the exact date comes back as first_seen_from), so NEVER compute the date yourself, the same wording must give the same window for every country (do not rely on date_from alone); first_seen_from (YYYY-MM-DD) = the same filter for an explicit calendar date the user named ('first seen since 20 September'), not for relative periods; if both are given first_seen_days wins; total then counts only such products (if the result has filter_note, the tool filtered the API pages itself and total is just the number of returned rows). win_badge=testing is the site's badge for 'active, under 14 days in ads'. min_price/max_price filter the catalog price; min_ads/max_ads filter the product's own ads count. sort_by: ads (default), ads_active, ads_in_period (needs a date window), price, visits (shop traffic), score (Winning Products: days x creatives x geos x reuploads). Returns total (the number of matching products — quote it as the number found; the rows are only the first limit of them), has_more, offset and data_through (last day the data is computed for; a date window is cut at it) and active_as_of (date of the daily snapshot the ads_active counters belong to). If a requested window starts after data_through there is no data for it yet: say the data is available through data_through, never print a period whose start is after its end. Rows with access=teaser have their ad counters blanked by the plan. FREE PLAN COUNTS: when the plan's archive window narrows a request, pagination.total_status is "restricted" and meta.plan_window_cutoff names the boundary — the count then describes the window actually searched, NOT the one requested, so a zero means "nothing in the archive window" and never "nothing exists". QUOTA: 1 MCP credit per DELIVERED result from your plan balance (free starter: 500 MCP credits lifetime; paid plans: 40,000/month; short pages auto-refund — you pay only for results you receive). Default page is 20 results = 20 MCP credits; pass limit (1–200) to size it. get_usage is free. Autonomous agents must be linked to a spytrend account to access data — an unlinked agent gets an actionable connect-your-account refusal (create agent credentials at spytrend.com/settings?tab=ai, or a human claims it by client_id), NOT a server error. Calls are rate-limited per authenticated user (deployment defaults: 60/minute and 1000/hour); a rate-limit refusal is an MCP tool error with structured error.code=rate_limit_exceeded, scope, window and retry_after_seconds. CONCURRENCY: heavy analytical calls (get_trends, search_ads, search_creatives) are admitted ONE AT A TIME per account — fanning out 5-10 of them in parallel does not go faster, it returns admission refusals for all but one. Issue heavy calls sequentially; light lookups (get_ad, get_advertiser, get_usage) are not gated. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: q, limit, domain, offset, +15 more. Returns: data, error, total, offset, +11 more

search_shopsSearch online stores and their trafficA
Read-only
Inspect

Search ONLINE STORES — the same catalogue as the website's /shops page (not every domain: general sites such as google.com or youtube.com are not in it). Each row carries traffic, commerce and advertising intelligence for one store domain. Shops advertising now in a country ("shops with fresh/active ads in Mexico"): country= + has_ads=true (only shops with ACTIVE ads now; add min_ads=N for a floor) + sort_by=ads — do NOT use search_ads for this; there is no separate freshness-window filter. visits is a MONTHLY estimate for traffic_as_of (not live traffic); fetched_at is ingestion time. Judge every estimate using traffic_quality, traffic_confidence, traffic_is_small, traffic_is_data_from_ga, traffic_data_status and history. traffic_paid_share is display + paid-search + paid-social share; trust it only when traffic_sources_available=true. visits_growth_pct is latest-vs-previous month PERCENT; min_growth and sort_by=growth only return growth_qualified rows (current cohort, contiguous 3-month window, previous month >=10k, non-small estimate, confidence >=0.60). category is an estimated SITE category and may be missing/wrong; ai_category is Spytrend's AD category and is preferred for ad-market discovery. created_from/to filter domain_created: best available registration date of the REGISTRABLE ROOT, not product/subdomain launch or Spytrend first-seen. The ClickHouse row does not retain whether that date came from the preferred registry lookup or the legacy fallback. traffic_start_max compares the current estimate with the MAXIMUM of both preceding complete months and excludes stale/low-quality windows; combine with traffic_end_min. ads_monthly counts ads first observed by Spytrend (first_parsed_date), and each point has is_complete=false for the open current month. fb_signal is correlation_only, not causal attribution; honest statuses are correlated_growth, ad_growth_ahead, ad_growth_flat_traffic, ad_growth_declining_traffic, traffic_growth_without_fb_growth, stable_or_mixed and insufficient_signal. sort_by=relevance REQUIRES ai_category and is rejected otherwise. Sorts: visits/revenue/growth/ads/rank/backlinks/ai_traffic/products/fb_score/per_ad/relevance; sort_by=ads orders by the number of ACTIVE ads now (active_ads), not by total_ads — never describe it as 'sorted by total number of ads'; sort_by=revenue and min_revenue use website_value — the estimated VALUE of the site in USD, NOT revenue, and outliers with tiny traffic are possible. country/country_exclude match the shop's MAIN visitor country (top_country). An empty page carries a note explaining why. product_count is the number of products shown on the website shop card (the larger of the crawler counter and the real catalog size products_total). a separate legacy snapshot is kept alongside; never substitute its similarly named traffic fields for the primary visits/traffic_as_of contract. Returns total, has_more and offset; total is the exact number of matching stores and has_more is true whenever total > offset+rows. FREE SAMPLE: without a Shops subscription the catalogue returns a short preview (a few rows) whatever the limit and deeper offsets come back empty — the result then carries a note "Free sample: N of TOTAL…" and params.normalized limit (requested→delivered); say it is a sample of TOTAL stores, never that only N exist. Use get_shop for the full source payload. Saving shops is free. FREE PLAN COUNTS: when the plan's archive window narrows a request, pagination.total_status is "restricted" and meta.plan_window_cutoff names the boundary — the count then describes the window actually searched, NOT the one requested, so a zero means "nothing in the archive window" and never "nothing exists". QUOTA: 1 MCP credit per DELIVERED result from your plan balance (free starter: 500 MCP credits lifetime; paid plans: 40,000/month; short pages auto-refund — you pay only for results you receive). Default page is 20 results = 20 MCP credits; pass limit (1–200) to size it. get_usage is free. Autonomous agents must be linked to a spytrend account to access data — an unlinked agent gets an actionable connect-your-account refusal (create agent credentials at spytrend.com/settings?tab=ai, or a human claims it by client_id), NOT a server error. Calls are rate-limited per authenticated user (deployment defaults: 60/minute and 1000/hour); a rate-limit refusal is an MCP tool error with structured error.code=rate_limit_exceeded, scope, window and retry_after_seconds. CONCURRENCY: heavy analytical calls (get_trends, search_ads, search_creatives) are admitted ONE AT A TIME per account — fanning out 5-10 of them in parallel does not go faster, it returns admission refusals for all but one. Issue heavy calls sequentially; light lookups (get_ad, get_advertiser, get_usage) are not gated. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: q, limit, saved, offset, +36 more. Returns: data, meta, note, error, +5 more

search_webmastersSearch webmastersA
Read-only
Inspect

Search webmasters (affiliates) — a webmaster is a whole ad NETWORK (landing domains, pixels, pages and geos grouped as one). Copy workflow: search by domain, take the canonical UUID, then search_creatives/search_ads with webmaster_id. Finish with the most reused material: get_webmaster.top_creatives or search_creatives sort_by=total_ads; total_ads is how many ads reuse the same material over its lifetime, not a weekly debut count. Returns total/active counts, top countries and geo counts. Find by name or pixel_id/domain/page_id/resolved_ip. Filter by category, AI category/subcategory, countries, languages, platforms, format, current status, dates and count ranges. For a geo ranking combine countries + min_geo_share + sort_by=relevance. Save returned UUIDs with add_to_favorites. Exact pixel_id/domain/page_id/resolved_ip lookups use the webmaster's CURRENT canonical identifier membership; historical identifiers removed from a webmaster do not count as matches. Exact page_id results report fanpages_status as available, partial, unavailable or not_applicable. When available, the selected page is included in fanpages[] with life_status from the same page-lifetime source as /advertisers (alive/deleted/banned, or unknown when lifetime coverage has no row); when unavailable, an omitted fanpages[] is not evidence that the page is alive. FREE PLAN COUNTS: when the plan's archive window narrows a request, pagination.total_status is "restricted" and meta.plan_window_cutoff names the boundary — the count then describes the window actually searched, NOT the one requested, so a zero means "nothing in the archive window" and never "nothing exists". QUOTA: 1 MCP credit per DELIVERED result from your plan balance (free starter: 500 MCP credits lifetime; paid plans: 40,000/month; short pages auto-refund — you pay only for results you receive). Default page is 20 results = 20 MCP credits; pass limit (1–200) to size it. get_usage is free. Autonomous agents must be linked to a spytrend account to access data — an unlinked agent gets an actionable connect-your-account refusal (create agent credentials at spytrend.com/settings?tab=ai, or a human claims it by client_id), NOT a server error. Calls are rate-limited per authenticated user (deployment defaults: 60/minute and 1000/hour); a rate-limit refusal is an MCP tool error with structured error.code=rate_limit_exceeded, scope, window and retry_after_seconds. CONCURRENCY: heavy analytical calls (get_trends, search_ads, search_creatives) are admitted ONE AT A TIME per account — fanning out 5-10 of them in parallel does not go faster, it returns admission refusals for all but one. Issue heavy calls sequentially; light lookups (get_ad, get_advertiser, get_usage) are not gated. TIKTOK SOURCE: pass source="tiktok" to query the TIKTOK ad corpus instead of Meta. (The platforms filter does NOT do this — platforms are Meta publisher placements.) ⚠️ TIKTOK IS PAID PER ROW at a premium: every DELIVERED TikTok ad row costs 10 MCP credits and every TikTok webmaster row/card costs 10 MCP credits (Meta rows cost 1), deducted from the same MCP credit balance (paid plans: 40,000/month = up to 400 TikTok rows). Request small limits and narrow filters; you are charged only for rows actually delivered (short pages auto-refund; if the balance covers only part of the request, that part is delivered — a 3-row request on a 15-MCP credit balance returns 1 row and charges 10). TikTok requires a Pro-or-higher plan: free/starter callers and unlinked agents get an actionable upgrade refusal, never data and never a charge. TikTok rows have their OWN shape, returned under tiktok_data (verified live 2026-07-30): id/external_id (TikTok ad id), advertiser{id,external_id,name} plus advertiser_id (TikTok BUSINESS id), start_date/end_date (the ad's delivery window) and first_seen_date/last_seen_date (Spytrend indexing), days_active, is_active + status_today, ai_category/ai_subcategory, countries + targeting_geos + targeting_details (OS/age/gender/regions), audience_size, objective, sponsor (the 'paid for by' funder) and registry_location, landing_domain + link_url, body/title/call_to_action, creative_format, creative_id, creative_ad_count (how many ads reuse that creative), is_blurred/is_cloaked, and media[] with media_type + thumbnail_url on media-tt.spytrend.com. Media comes WITH the row — do NOT call get_media for TikTok ids (it serves Meta entities only). There are no TikTok engagement counters (plays/likes/comments/shares) on this surface. The TikTok feed serves the ARCHIVED TikTok corpus — exactly what the spytrend.com /ads TikTok tab shows — and pagination carries has_more/next_cursor plus total with total_status (exact, estimated or unavailable; unavailable is not zero). With source=tiktok rows are TikTok webmaster clusters. Supported TikTok webmaster filters: query, domain, countries (+min_geo_share), exclude_countries, ai_category (dominant), min_total_ads, min_active_ads, date_from/date_to, has_funder, sort_by=total_ads|active_ads|created_at|relevance, sort_order, offset (0-5000), limit (server caps TikTok at 100). Date filters select clusters whose activity window overlaps the requested period. Active means shown within the last 3 calendar days. Meta-only lookups, languages/platforms/creative_format(s), status_today, ai_subcategory, folder_id and saved are REJECTED before charging. Default TikTok limit is 10; each delivered row costs 10 MCP credits. PRICING: price × number of filters set (min 1), on paid plans ×1 after 500 MCP credits/month; one-time consent via accept_pricing_terms; before calling, get the maximum debit from estimate_cost (free) and tell the user.

Inputs: limit, query, saved, domain, +24 more. Returns: data, meta, error, params, +4 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Manage ad campaigns across Meta, Google, and TikTok, create campaigns, analyze performance, spy on competitors, and generate AI creatives.
      5
      20
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP clients to discover ecommerce brands that are newly advertising, scaling, struggling, or stopped on Meta; look up a brand's ad history and trend; and inspect any store's platform, tracking pixels, and marketing tools for research and outreach.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources