
RivalSweeper MCP server
Which servers in the official MCP registry are RivalSweeper's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-21
- Registry namecom.rivalsweeper/signalsverified in the MCP registry
The registry name sits under rivalsweeper.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools35
- Server calls itselfrivalsweeper-signals
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 1557 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 4 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer533 ms
- Space in an agent's context≈ 5,456 tokensthe definitions of all its tools (37), which an agent carries on every turn
- Tool definitionsA · 97 of 100
- Typed results0 of 37 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 6 of 37
What an agent can do with it
- cannot · Track competitor price changes and markdowns every day
- not sure · Spot rival product launches, removed lines and restocks
- not sure · Check whether competitor discount claims were real
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
check_brand_data_coverageCheck which competitive signals RivalSweeper has for an eCommerce domain, with per-signal freshness. Free and non-billable - call this before any billable tool so you never pay for a domain we do not cover.
get_active_promotions_and_couponsActive promotions/discount codes for a brand: code, discount type/value, min order, validity window. Freshness-stamped. Included in RivalSweeper plans (developer API keys: 1 credit, no data = no charge).
get_brand_price_statisticsPrice statistics (min/max/avg/median) plus recent product samples for a brand, optionally filtered by product-name query. Freshness-stamped. Included in RivalSweeper plans (developer API keys: 1 credit, no data = no charge).
find_closest_competitor_brandsThe brand's last-known DNA competitor set: the closest competing brands RivalSweeper identified for a domain, each with name, website, country, home-market flag and match tier, plus the brand's own DNA profile. Freshness-stamped. Included…
get_homepage_top_linksA 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…
get_ai_agent_readiness_scoreRivalSweeper 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…
get_full_brand_snapshotBundle: 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).
get_my_usage_and_planYour 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…
get_significant_competitor_changesRecent 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…
request_missing_data_signalTell RivalSweeper exactly what signal you need for a domain. We prioritize data collection based on demand. Use this when check_brand_data_coverage shows a signal is missing or when you need data we do not yet track. Free and non-billable.
request_new_brand_monitoringAdd 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…
list_my_tracked_brandsThe brands in your RivalSweeper account: your own site(s) and the rival brands you monitor, with status. Use it to see which domains the other tools can answer for.
get_cross_channel_ads_overviewCross-channel ads picture (Meta, Google and others) for your brand vs rivals: live and new ads, channel mix, coordinated pushes, gaps vs you, and prioritized insights with suggested actions.
get_brand_radar_assortment_gapsWeekly 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.
get_homepage_product_shelf_and_markdownsWhich products each brand keeps on its homepage shelf and for how long (persistence, slots, best position), with price and markdown - a read on what brands are pushing. Window in days (7-365, default 90).
get_newly_published_products_and_pagesNewly published products and pages per brand (from sitemaps), newest first, with type and tags. Default last 7 days, up to 50 rows (max 200).
get_technology_stackThe software services each brand runs (analytics, marketing, payments, reviews, search, etc.) as detected by RivalSweeper.
get_email_newsletter_insightsA brand's email newsletter patterns: cadence, send times, themes and offers, from RivalSweeper's newsletter tracking.
get_social_media_channels_and_followersSocial network presence per brand: channels, followers and posting cadence.
get_competitor_moves_feedWhat your rivals changed, newest first: technology and providers, shipping, ads, marketing messages, AI citations, agent readiness, hiring, performance, bestsellers and more (RivalSweeper's Domain Moves feed). Default last 7 days.
get_predicted_competitor_movesRivalSweeper's weekly predictions of each tracked brand's likely next moves (e.g. a sale, a launch), with confidence, the evidence behind it, and a short narrative.
get_upcoming_events_news_and_activityYour dashboard agenda: upcoming holidays and retail events in the countries your brands ship to, news mentions (7 days) and recent catalog activity per brand.
get_my_rivalsweeper_todo_listAction 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.
find_ads_with_broken_pages_or_expired_offersAd & Deal Health: live ads that point to broken or out-of-stock pages, ads promoting expired offers, evergreen 'urgency' claims, and expired homepage banners. Checks your own store by default, or one named rival.
get_discount_frequency_and_depthHow often and how deep each brand discounts: promo days vs observed days, average and max discount %, and promo types, over a window (7-365 days, default 30).
get_most_discounted_productsA brand's most-discounted products right now (by % or amount) or its newest discounts, with price, full price and discount.
get_how_ai_models_describe_brandHow 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…
get_brand_swot_analysisRivalSweeper's SWOT analysis of a brand over time: strengths, weaknesses, opportunities and threats, and how they changed.
get_homepage_analysisRivalSweeper's analysis of a brand's homepage: what it features and emphasizes, offers and messaging, and how it compares with rivals.
get_product_page_analysisRivalSweeper's analysis of a brand's product pages: the tactics they use (content, imagery, trust signals, offers, cross-sell).
get_catalog_analysisRivalSweeper's analysis of a brand's product catalog: assortment, categories and pricing structure.
get_customer_reviews_analysisRivalSweeper's analysis of a brand's customer reviews: recurring themes, sentiment, praise and complaints.
get_ai_model_citation_rateWhether AI models cite each brand when answering shopping questions: citation rate overall and by AI platform, plus recent example queries and the cited URLs. RivalSweeper currently samples Google Gemini and OpenAI's open-weight GPT-OSS…
get_ai_shopping_agent_checkout_raceRivalSweeper'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.
get_job_openings_and_hiring_trendsOpen 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.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"signals": {
"type": "http",
"url": "https://mcp.rivalsweeper.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http rivalsweeper https://mcp.rivalsweeper.com/mcpclaude.ai, ChatGPT and other clients: add https://mcp.rivalsweeper.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.