RivalSweeper Signals MCP Server

Check which competitive signals RivalSweeper has for an eCommerce domain, with per-signal freshness (for prices: when a price was last read, plus the share of priced products read in the last 7 days; records counts products, each product once however many variant rows it has; for large catalogs these come from a sample and are marked records_approximate). A signal is available exactly when its tool has data: promotions counts the live offers get_active_promotions_and_coupons returns, prices follow get_brand_price_statistics. Free and non-billable.

Price statistics (min/max/avg/median) plus recent product samples for a brand, optionally filtered by product-name query. Freshness = when a price was last read; stats also give the share of products whose price was read in the last 7 days and the median read time, and a note flags catalogs where most prices are older. Included in RivalSweeper plans (developer API keys: 1 credit, no data = no charge).

Weekly Brand Radar for your store vs rivals: brands you are missing (white space), where you lead (moat), depth gaps, price position and discount pressure per brand. For multi-brand retailers; returns no data for single-brand stores.

RivalSweeper's SWOT analysis of a brand over time: strengths, weaknesses, opportunities and threats, and how they changed.

RivalSweeper's analysis of a brand's homepage: what it features and emphasizes, offers and messaging, and how it compares with rivals.

Which products each brand keeps on its homepage and for how long (persistence = share of the observed days on the homepage, slots, best position), with price, currency and markdown, plus the categories it features - a read on what brands are pushing. Window in days (7-365, default 90).

A brand's current homepage top links (up to 10) enriched from its catalog and grouped into Products, Categories and Content, in that order. Per link: title, vendor, price + compare-at/on-sale, currency, stock status, URL status (active/inactive), review rating, homepage position, anchor text and last update. A top-level 'comment' flags when pricing and/or stock status are not captured for the domain. Included in RivalSweeper plans (developer API keys: 2 credits, no data = no charge).

Tell RivalSweeper exactly what signal you need for a domain. For a signal that is missing for a domain or that RivalSweeper does not track yet. We prioritize data collection based on demand. Free and non-billable.

Add a rival domain to monitoring. Signed in with RivalSweeper: adds it to your monitored rivals right away (company Admins only; your plan or trial domain limit applies), with first data within about 24h. Developer API keys: queues a monitoring request (needs a positive prepaid balance; first data in 24-72h). Free.

Active promotions/discount codes for a brand: code, discount, terms, valid_until. Only live offers (expired and single-use codes left out). Each row says how it is known: verification = seen_on_brand_homepage (read off the brand's own homepage) or third_party_unverified (listed on public coupon sites, not tested at checkout). Freshness-stamped. Included in RivalSweeper plans (developer API keys: 1 credit, no data = no charge).

Ad & Deal Health, untrimmed: every live ad that points to a broken or out-of-stock page, promotes an expired offer, keeps an evergreen 'urgency' claim, or could not be checked, plus expired homepage banners, with the full ad text, links, landing check and product read. Checks your own store by default, or one named rival.

RivalSweeper 6-pillar AI/agent-readiness score for a domain (schema.org, technical access, content quality, trust, AI-specific, entity recognition) with tier and highlights. Uniquely RivalSweeper data. Included in RivalSweeper plans (developer API keys: 1 credit, no data = no charge).

RivalSweeper's analysis of a brand's product catalog: assortment, categories and pricing structure.

The brand's last-known DNA competitor set: the closest competing brands RivalSweeper identified for a domain, each with name, website, country and match tier, plus the brand's own DNA profile. Freshness-stamped. Included in RivalSweeper plans (developer API keys: 2 credits, no data = no charge).

What your rivals changed, newest first: technology and providers, shipping, ads, marketing messages, AI citations, agent readiness, hiring, performance, bestsellers, Terms / privacy / return / shipping policy and other info page changes (type 'Content Pages', with the number of changes per page), and more (RivalSweeper's Domain Moves feed). Default last 7 days.

Cross-channel ads picture (Meta, Google and others) for your brand vs rivals: live and new ads, reach, channel mix, 12 weeks of launches per channel and placement, coordinated pushes, gaps vs you, the Google country matrix, Meta placement concentration, and prioritized insights with suggested actions. Full data, nothing trimmed.

RivalSweeper's analysis of a brand's customer reviews: recurring themes, sentiment, praise and complaints.

How often and how deep each brand discounts, over a window (7-365 days, default 30), from two separate readings: homepage_banner = days a promotion banner was on the brand's homepage (read from our homepage captures; 'not_measured' when we hold no capture in the window), and product_markdowns = products whose price, read in the window, is below their full price, with average and max markdown %, in one store and currency per brand. A brand can run product markdowns with no homepage banner.

A brand's email newsletter patterns: cadence, send times, themes and offers, from RivalSweeper's newsletter tracking.

Bundle: all current signals for one brand-day - promotions, price stats + samples, AI-readiness - in one call. Included in RivalSweeper plans (developer API keys: 15 credits, no data = no charge).

Everything on the app's Google Ads tab for your brand vs rivals, untrimmed: live, new and stopped ads, every country, Google Shopping, formats, targeting, creative freshness (median ad age, weekly series), all topics, where ads show, reach, alerts, advertiser accounts. Name exactly one brand to also get its Google creatives, 200 per page (creatives_offset for the next page; `total` tells how many exist). Up to 6 brands per call.

How large language models describe a brand when asked shopping questions, by aspect: brand_reputation, competitor_comparison, product_recommendation, brand_review, industry_landscape, brand_sentiment, recommendation_gap. RivalSweeper currently samples Google Gemini and OpenAI's open-weight GPT-OSS models.

Open roles per brand by department and location, change vs last check, top job titles and newly added or removed jobs - an early read on where a rival is investing.

Everything on the app's Meta Ads tab for your brand vs rivals, untrimmed: reach (accounts that saw the ads, UK/EU only) and reach by market, all top ads by reach and by days running plus ended long-runners (full copy, links), hook angles with what each brand tests vs funds, hooks by country with every angle count, the punch of each analysed ad read from the creative itself (image, carousel cards or the whole video with its sound: the idea that stops the scroll, on-screen text, first words spoken, format, references) with context only where a source is linked (calendar event named in the ad, a page about the reference) and what each brand tests vs funds per punch type, offers and codes, CTA mix, formats, languages, creators, new promoters, campaign tags, sites and every promoted page (name, price, stock, category, live ads, reach, broken links). Up to 6 brands per call.

Whether AI models mention each brand in their answers, split by question kind: brand_named = questions that name the brand ("What do you know about X?", "Compare X with its competitors": shows whether models know the brand, not whether they recommend it unprompted) and unbranded = shopping questions that do not name it (the recommendation test). Each with rate, by model (and the platform serving it), and recent examples. Our own prompt-generation queries (keyword and shopper-question lists) are not citation tests and are left out.

A brand's most-discounted products right now (by % or amount) or its newest discounts, with price, full price and discount.

Products and pages RivalSweeper first found on each brand's site (sitemaps and catalog feeds) in the last N days, newest first, interleaved across brands. Shopify variant URLs are folded into their product, and a product that only gained new sizes/colours is labelled so. Each item has its tags (names), first_seen (when RivalSweeper first found it: usually within a day of publication, not the brand's own publish date) and sitemap_lastmod when the sitemap gives one; per-brand counts come first. Pages found in a brand's first days of tracking are left out (they existed before). Default last 7 days, up to 50 items (max 200).

RivalSweeper's weekly prediction cards for each tracked rival, as on the Predictions page: what just happened, what is coming up (e.g. Black Friday on last year's timing) and where their ads outpace you. Each card has the why, a suggested move with its date, and dated proof (receipts, article links).

RivalSweeper's analysis of a brand's product pages: the tactics they use (content, imagery, trust signals, offers, cross-sell).

Action items RivalSweeper raised for your team (e.g. fix a broken ad landing page, respond to a rival promotion), with priority, status, owner and due date. Default: pending items.

RivalSweeper's weekly race of AI shopping agents buying the same product from your store and rivals: which stores an agent could complete checkout on, where it got stuck, KPIs and findings.

Recent significant changes for a competitor: price drops/increases >10%, new promotions, stock-status flips. Returns a chronological alert feed with a summary. Configurable window (1-90 days, default 7). Included in RivalSweeper plans (developer API keys: 2 credits, no data = no charge).

Social network presence per brand: channels, followers and posting cadence.

The technology each brand runs, per brand: e-commerce platform first, then payments, cross-border, email/SMS, reviews and loyalty, search and personalisation, customer service, shipping, analytics, advertising, consent/security and infrastructure, each with its category names. Social networks the site links to are listed apart (a profile link is not a tool the store runs). Up to 40 technologies per brand by default (max_per_brand up to 200); the count left out is stated per brand.

The brands in your RivalSweeper account: your own site(s) and the rival brands you monitor, with status: the domains this connector can answer for.

Your dashboard agenda: upcoming holidays and retail events in the countries your brands ship to, news mentions (7 days) and recent catalog activity per brand.

Your own account status. Signed in with RivalSweeper: your plan, tool calls used this month vs. the plan limit, and the domains you can query. Developer API key: prepaid credit balance plus calls and credits per tool over a look-back window (default 30 days). Free; only ever returns your own usage.