ConvRadar

ConvRadar is an MCP server that turns your Google Analytics 4 data into a working conversation about conversion rate optimization. Instead of staring at dashboards trying to figure out why revenue dropped last week, you ask Claude — and Claude pulls the data, finds the real problem, and tells you what to do about it. Most analytics tools stop at "your conversion rate is down 12%." ConvRadar continues: which segment caused it, which traffic source is leaking budget, which landing page is underperforming, which device tier is broken, and what to fix first. Every recommendation is tied to specific numbers from your own GA4 data — not generic best practices. What you can ask: "Why did conversions drop last week?" → diagnoses which segment is responsible "Run a full CRO audit on my store" → headline KPIs, funnel breakdown, traffic quality, top problems ranked by impact "Which traffic sources are wasting my budget?" → relative efficiency analysis across paid sources "What's broken on mobile?" → device-level conversion gaps with concrete next steps "Find anomalies in my funnel this month" → statistically significant spikes and drops with context What's inside: 22 tools covering overview metrics, funnel analysis, traffic and device breakdowns, landing page performance, product-level diagnosis, geo-efficiency, anomaly detection, segment comparison, and benchmark comparison. Plus a built-in CRO hypothesis library — 500+ documented patterns from real e-commerce and SaaS optimization work, searchable by problem. Built for: e-commerce operators, SaaS founders, growth marketers, and CRO consultants who use GA4 and want fast diagnostics without spending an hour clicking through Explorations. How it works: connect your GA4 property via OAuth, subscribe at convradar.com ($9.99/month, 7-day free trial), and start asking. All recommendations rely on relative metrics (conversion rates, session shares, purchase ratios) — no cost data required.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://convradar--pikaivan.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "ConvRadar": {
      "url": "https://convradar--pikaivan.run.tools"
    }
  }
}

能力清单

工具	说明
cr_get_account_info	ConvRadar (GA4 analytics): the connected GA4 property's name, currency, timezone, available data window, AND the property's website origin (scheme://host) derived from page_location data. Always call this at the start of a session. Combine `website_url` with paths returned by cr_get_landing_pages, cr_get_product_performance, or cr_query_metrics to build absolute URLs for cr_capture_via_web_fetch — no need to ask the user for the domain unless website_url comes back null.
cr_get_overview_metrics	ConvRadar (GA4 analytics): headline KPIs for the connected GA4 property — sessions, conversion rate, revenue, AOV — for a date window with deltas vs the prior period of equal length. Use when the user asks about overall performance, "how is the site doing", week-over-week or month-over-month conversion/revenue trends. date_from/date_to are ISO YYYY-MM-DD. Default = last 30 days. Max window 90 days.
cr_get_traffic_breakdown	ConvRadar (GA4 analytics): top traffic sources for the connected GA4 property, broken down by (source, medium) with sessions, users, purchases, revenue, conversion rate. Use when the user asks about traffic sources, channels, where users come from, top-performing campaigns, organic vs paid mix. sort_by ∈ {"revenue", "sessions"}. Returns up to top_n combos (capped at 25).
cr_get_device_breakdown	ConvRadar (GA4 analytics): mobile vs desktop vs tablet for the connected GA4 property — session shares, per-device conversion rate, engagement, revenue. Use when the user asks about device performance, mobile vs desktop comparison, why mobile underperforms, or device-level conversion rates.
cr_get_landing_pages	ConvRadar (GA4 analytics): top landing pages on the connected GA4 property — sessions, engagement rate, bounce rate, avg session duration, purchases, revenue. Use when the user asks about landing-page performance, which pages drive traffic, high-bounce pages, top-converting pages. sort_by ∈ {"sessions", "revenue", "purchases"}. Returns up to top_n (capped at 25). This output identifies which pages have problems but not why. Fixing specific UI / copy / layout issues requires the page itself: fetch via `cr_capture_via_web_fetch`, ask for a mobile screenshot if a mobile segment is the dominant gap, and ask the user about pop-ups or walls between landing and conversion. Full policy: `/verification-policy`.
cr_get_funnel	ConvRadar (GA4 analytics): step-by-step e-commerce funnel with conversion rate at each step, the biggest leak, and the top N leaks ranked by drop %. Use when the user asks about the conversion funnel, drop-off, where users stop, "why aren't people buying", "top problems in my funnel", checkout abandonment. Default funnel: page_view → view_item → add_to_cart → begin_checkout → purchase (4 transitions). Override `steps` for sites with non-standard events. `top_leaks` caps the ranked list (default 4 = all transitions of the default funnel; max equals number of transitions). This output names the leakiest step transitions but not the on-page cause. Recommendations require fetching the implicated page via `cr_capture_via_web_fetch`, a mobile screenshot when mobile-skewed, and asking the user about between-step blockers (sign-up walls, address modals, age gates, KYC). Full policy: `/verification-policy`.
cr_get_geo_breakdown	ConvRadar (GA4 analytics): top countries by sessions or revenue, with conversion rate per country. Use when the user asks about geographic performance, "where are my users from", country-level conversion, international markets. sort_by ∈ {"sessions", "revenue", "purchases"}. Returns up to top_n (capped at 25) countries.
cr_get_product_performance	ConvRadar (GA4 analytics): top products by revenue, views, or purchases — with cart-to-view + purchase-to-view rates per item. Use when the user asks about product/SKU performance, best/worst sellers, which items convert, item-level analysis, e-commerce catalog insights. sort_by ∈ {"revenue", "items_purchased", "items_viewed"}. Optional `category` filter narrows to a single item_category. Returns up to top_n (capped at 25).
cr_compare_segments	ConvRadar (GA4 analytics): compare two segments side-by-side on the same metrics with computed deltas. Use when the user asks "is mobile underperforming desktop", "is paid worse than organic", "how does the US compare to UK", "is new traffic converting like returning". dimension ∈ {"device", "source", "country", "new_vs_returning"}. value_a / value_b are the two values to compare (case-insensitive for device/new_vs_returning; for source pass "google / organic" syntax). This output quantifies the gap between segments but not the on-page cause. Recommendations require fetching the page implicated by the worse segment via `cr_capture_via_web_fetch`, a mobile screenshot if the dimension is `device` and mobile is worse, and asking the user about between-step differences. Full policy: `/verification-policy`.
cr_get_product_analysis	ConvRadar (GA4 analytics): pre-computed product diagnosis — every SKU classified as underperforming / watchlist / healthy / no_purchases / low_data, with broken-funnel-step (view→cart, cart→checkout, checkout→purchase), weekly revenue opportunity, and anomaly flags (3-week declines, drop %). Use when the user asks "which products are problem children", "where am I losing money on SKUs", "underperforming items", "anomalies", or wants the diagnostic view rather than raw metrics. Filter to one classification with `status`. Returns the latest completed run; if none exists, advises running it from the ConvRadar web panel. status ∈ {"underperforming", "watchlist", "healthy", "no_purchases", "low_data"} or omit for all. top_n caps at 25. This output classifies underperforming SKUs and the broken funnel step but not the on-PDP cause. Recommendations require fetching each implicated PDP via `cr_capture_via_web_fetch`, a mobile screenshot if the broken step is view→cart and the SKU's traffic skews mobile, and asking the user about between-step blockers for cart→checkout / checkout→purchase issues. Full policy: `/verification-policy`.
cr_find_conversion_anomalies	ConvRadar (GA4 analytics): finds statistically-significant anomalies (spikes and drops) in your daily metrics over the last N days. Uses a 28-day rolling baseline with weekly seasonality adjustment. Use when the user asks "is anything weird in my data", "find anomalies", "is something broken", "did anything spike or drop". Returns flagged dates with severity (notable \| severe). metrics ∈ {"sessions", "purchases", "revenue", "conversion_rate"}. Default: all four. This output flags an anomaly's date and severity but not its cause. Attributing the cause requires localizing the segment via `cr_diagnose_funnel_drop`, fetching the implicated page via `cr_capture_via_web_fetch`, a mobile screenshot if the anomaly concentrates there, and asking the user what changed around the date (deploys, content swaps, paid-traffic changes, tracking edits). Full policy: `/verification-policy`.
cr_diagnose_funnel_drop	ConvRadar (GA4 analytics): given a current vs prior period, find which segments contribute most to a drop (or rise) in conversion_rate / revenue / purchases. Splits across device, source, country, landing_page. Use when the user asks "why did my conversion drop", "where is the leak", "diagnose my checkout drop", "what's hurting my numbers", "what changed". This is the core 'find the leak' tool. Compares the last N days vs the immediately-preceding N days. metric ∈ {"conversion_rate", "revenue", "purchases"}. This output names the segments contributing most to a drop but not the on-page cause. Recommendations require fetching the implicated page via `cr_capture_via_web_fetch`, a mobile screenshot if a mobile segment is the dominant gap, and asking the user about between-step blockers when the leak concentrates at a single transition. Full policy: `/verification-policy`.
cr_compare_to_benchmark	ConvRadar (GA4 analytics): compare your headline metrics (conversion rate, AOV, bounce rate, engagement rate) against industry benchmarks for your vertical. Use when the user asks "how do I compare to industry", "are my numbers good", "benchmark my site", "is my conversion rate normal". vertical: when omitted, read from the connected property's `vertical` column (set during onboarding). Falls back to ecommerce_general if not set. Override with one of: ecommerce_general, dtc_apparel, beauty_ecom, ecom_electronics, saas, marketplace, subscription_ecom.
cr_detect_traffic_quality_change	ConvRadar (GA4 analytics): detect anomalies in traffic mix and per-source sessions over time. Flags large shifts in traffic-source share (e.g., paid traffic dropped from 40% to 15%) or anomalous spikes/drops in any top source's daily sessions. Use when the user asks "did my traffic mix change", "is one channel acting weird", "did paid traffic drop", "what's happening with my organic traffic". Limited to top sources by volume so the response stays focused. top_n_sources caps how many sources we monitor (default 8, max 25).
cr_describe_data	ConvRadar (GA4 analytics): describe what data is available for the connected GA4 property — list of fact tables with their queryable dimensions and metrics, distinct event names actually present, and the date window of the data. Use this once at the start of an analysis session before composing a `cr_query_metrics` call. The output tells Claude exactly which dimensions and metrics are valid combinations.
cr_query_metrics	ConvRadar (GA4 analytics): flexible aggregation over any ga4_fact_* table — pick metrics + optional dimensions and the tool finds the right fact table, runs the query, and aggregates. Use this for ad-hoc questions like "how many users yesterday", "revenue by day", "purchase events by country last week", "sessions by device for april". For the fixed dashboards (overview, traffic, landing, etc.) prefer the dedicated `cr_get_*` tools — they're tuned for those shapes. - `metrics`: required, snake_case column names (e.g. `["total_users", "purchase_revenue"]`). Run `cr_describe_data` first if you don't know the names. - `dimensions`: optional. Use `["date"]` for a time series, `[]` (or omit) for a grand total. Multi-dim grouping is supported. - `filters`: optional dict — value can be scalar (`"mobile"`), list (`["purchase","add_to_cart"]`), or 2-tuple (range). - Date window default last 30 days, max 90. This is an ad-hoc aggregation tool — its output is metrics, not diagnoses. If the user's question leads to a recommendation, the recommendation requires fetching the implicated page via `cr_capture_via_web_fetch`, a mobile screenshot when mobile-skewed, and asking the user about between-step blockers. Full policy: `/verification-policy`.
cr_assess_traffic_quality	ConvRadar (GA4 analytics): scores how much of the property's traffic looks like analytics noise (referral spam, internal/test traffic, datacenter sources, low-quality paid) and estimates how that noise distorts headline conversion rate and revenue. Use this BEFORE any CRO / funnel diagnosis. If estimated_noise_share ≥ 15%, the conversion-rate "drop" the user is worried about may be partially a tracking issue, not a real funnel problem. Each finding carries inline GA4 cleanup instructions (regex for unwanted-referrals filter, internal traffic filter setup, etc.). sensitivity ∈ {"conservative" (default, threshold 75), "normal" (60), "aggressive" (45)}. Date window default last 28 days; max 90. comparison_days default 28.
cr_list_hypotheses	ConvRadar (CRO library): browse the hypothesis catalog. Filter by category (e.g. 'pdp_clarity', 'checkout_friction') or vertical (e.g. 'dtc_apparel', 'beauty_ecom'). Returns a paginated list with id, title, category, expected impact range. Use when the user asks "what hypotheses do you have", "show me PDP hypotheses", "what tests can I run for cart abandonment". Returns the catalog itself, not matches against a specific finding — call cr_get_hypothesis for full detail on one entry.
cr_get_hypothesis	ConvRadar (CRO library): full content for one hypothesis by id (e.g. 'H-PDP-001'). Returns description, applicable verticals, inspection targets, conclusion rules, expected impact range, A/B test design, remediation hint, capture-set info, and which triggers it's attached to. Use when the user asks "tell me more about H-PDP-001", "what's the test for this hypothesis", "how do I verify it".
cr_capture_via_web_fetch	ConvRadar (verification): fetch a URL server-side and return its HTML body so Claude can extract observables. Cached by (capture_set_id, url) for 7 days; UTM params are stripped before caching. capture_set_id: one of the 7 seeded capture sets (e.g. 'CS-pdp-desktop'). url: the page to inspect. Returns raw HTML only. Cannot see: (1) JS-rendered DOM (SPA frameworks inject content client-side after hydration); (2) mobile-specific layout (responsive sites return identical markup — only media queries differ); (3) cross-step flow (modals / walls / gates between funnel steps). When any of these matter, ask the user for a screenshot — list specific URLs and viewports, not a conditional "if it's a SPA, send one". Forbidden conclusions and the full protocol: `/verification-policy`.
cr_get_current_state	ConvRadar (cross-session continuity): per-tenant snapshot of what's already in flight — last 30-day overview metrics, up to 10 active hypotheses (status surfaced/testing/confirmed sorted by marked_at DESC), last 5 logged changes, and ≤3 most recent open findings. Call this at the start of any session, especially when the user asks "what's in work / in progress / pending / what was I doing", before re-running diagnostics. Lets you continue prior work without making the user re-explain.
cr_full_audit	ConvRadar (golden first-run audit): runs a complete diagnostic in one call — headline KPIs vs prior period, biggest funnel leak, top 3 traffic sources, top 3 landing pages, anomalies, segment drops, and benchmark comparison. Returns 2–5 ranked actionable findings with next-step actions and matched hypotheses. Use as the first tool on a new connection or whenever the user asks for a full audit. Trigger phrases: "run a full audit", "audit my analytics", "where do I start", "give me the diagnostic", "what's wrong with my conversion", "first-time analysis", "complete check". date_from/date_to are optional ISO YYYY-MM-DD; defaults to last 30 days vs prior 30 days. Read-only. Output ≈ 4–8 KB. Findings reference the next tool to call (cr_capture_via_web_fetch, cr_diagnose_funnel_drop) — full guardrails: `/verification-policy`.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。