ConvRadar

pikaivan/convradar-mcp

Connects Claude directly to your Google Analytics 4 property via OAuth and exposes about 20 diagnostic tools for answering conversion questions in natural language. Ask where your funnel is dropping, whether mobile conversion tanked last week, or how landing pages compare, and it pulls the right GA4 Data API slice, runs the analysis, and returns numbers with a recommendation. Stores hypotheses between sessions so follow-up questions have context. Hosted service at $9.99/month, works through mcp-remote for desktop clients or as a custom connector in Claude.ai and ChatGPT. You're trading setup friction for a conversion analyst that lives inside your editor.

tools: 22
transport: HTTP
last updated: Aug 12, 2026

View on GitHub

Tools

22 tools

Public tool metadata for what this MCP can expose to an agent.

cr_get_account_infoConvRadar (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...

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...

No parameter schema in public metadata yet.

cr_get_overview_metricsConvRadar (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 m...2 params

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 m...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

cr_get_traffic_breakdownConvRadar (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, or...4 params

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, or...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

sort_bystring

Metric to rank channels by. One of: 'revenue' (default), 'sessions', 'conversions', 'conversion_rate'.default: revenue

top_ninteger

How many rows to return. Default 10, max 25.default: 10

cr_get_device_breakdownConvRadar (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 con...2 params

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 con...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

cr_get_landing_pagesConvRadar (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 pa...4 params

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 pa...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

sort_bystring

Metric to rank landing pages by. One of: 'sessions' (default), 'revenue', 'conversion_rate', 'bounce_rate'.default: sessions

top_ninteger

How many rows to return. Default 10, max 25.default: 10

cr_get_funnelConvRadar (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...4 params

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...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

stepsvalue

Custom event sequence for the funnel. Default: GA4 e-commerce steps (page_view → view_item → add_to_cart → begin_checkout → purchase).

top_leaksinteger

How many biggest step-to-step drop-offs to surface. Default 4.default: 4

cr_get_geo_breakdownConvRadar (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"}. R...4 params

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"}. R...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

sort_bystring

Metric to rank countries/regions by. One of: 'sessions' (default), 'revenue', 'conversion_rate'.default: sessions

top_ninteger

How many rows to return. Default 10, max 25.default: 10

cr_get_product_performanceConvRadar (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_...5 params

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_...

Parameters* required

categoryvalue

Restrict to one product category (item_category from GA4). None = all categories.

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

sort_bystring

Metric to rank products by. One of: 'revenue' (default), 'sessions', 'add_to_carts', 'conversion_rate'.default: revenue

top_ninteger

How many rows to return. Default 10, max 25.default: 10

cr_compare_segmentsConvRadar (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". dimensi...5 params

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". dimensi...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

dimensionstring

Which GA4 dimension to split on, e.g. 'device_category', 'country', 'session_source_medium', 'session_default_channel_group'.

value_astring

First segment value, e.g. 'mobile' or 'Google / cpc'.

value_bstring

Second segment value, e.g. 'desktop' or 'Google / organic'.

cr_get_product_analysisConvRadar (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 dec...2 params

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 dec...

Parameters* required

statusvalue

Optional filter on product trend status. One of: 'rising', 'declining', 'stable', or None for all.

top_ninteger

How many rows to return. Default 10, max 25.default: 10

cr_find_conversion_anomaliesConvRadar (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 s...3 params

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 s...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

metricsvalue

Which metric families to scan for anomalies. None = all (sessions, conversions, revenue, AOV, funnel steps).

cr_diagnose_funnel_dropConvRadar (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...4 params

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...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

metricstring

Which headline metric drove the drop being diagnosed. One of: 'conversion_rate' (default), 'revenue', 'sessions', 'aov'.default: conversion_rate

top_n_per_dimensioninteger

How many top-contributing segments to surface per dimension. Default 3.default: 3

cr_compare_to_benchmarkConvRadar (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 rat...3 params

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 rat...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

verticalvalue

Industry vertical to benchmark against (e.g. 'dtc_apparel', 'beauty', 'electronics', 'saas'). None = auto-detect from the connected property.

cr_detect_traffic_quality_changeConvRadar (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 tr...3 params

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 tr...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

top_n_sourcesinteger

How many traffic sources to inspect for quality changes. Default 8.default: 8

cr_describe_dataConvRadar (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 sessio...

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 sessio...

No parameter schema in public metadata yet.

cr_query_metricsConvRadar (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 ev...7 params

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 ev...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

dimensionsvalue

Optional dimensions to group rows by, e.g. ['device_category', 'country']. None = no grouping, returns a single aggregated row.

filtersvalue

Optional {dimension: value} pairs to filter rows before aggregation. E.g. {'device_category': 'mobile'}.

metricsarray

Metric names to aggregate, e.g. ['sessions', 'purchase_revenue']. Call cr_describe_data first for the full catalog and which dimensions each metric supports.

sort_byvalue

Metric name to sort rows by (descending). None = the first metric in `metrics`.

top_ninteger

Maximum rows to return after grouping. Default 50.default: 25

cr_assess_traffic_qualityConvRadar (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 / fu...6 params

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 / fu...

Parameters* required

comparison_daysinteger

Baseline window in days that the current window is compared against. Default 28.default: 28

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

min_sessionsinteger

Minimum sessions a source needs in the current window before being scored. Default 50.default: 50

sensitivitystring

How aggressively to flag quality changes. One of: 'conservative' (default), 'balanced', 'aggressive'.default: conservative

top_ninteger

How many traffic sources to inspect. Default 10.default: 10

cr_list_hypothesesConvRadar (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 hypothes...3 params

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 hypothes...

Parameters* required

categoryvalue

CRO category filter, e.g. 'mobile-checkout', 'pricing-display', 'trust-signals'. None = all 21 categories.

top_ninteger

Maximum hypotheses to return. Default 10.default: 10

verticalvalue

Industry vertical filter (same options as cr_compare_to_benchmark). None = auto-detect from the property.

cr_get_hypothesisConvRadar (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....1 params

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....

Parameters* required

hypothesis_idstring

Hypothesis ID returned by cr_list_hypotheses (e.g. 'mobile-paypal-button-v3').

cr_capture_via_web_fetchConvRadar (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...2 params

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...

Parameters* required

capture_set_idstring

Unique ID grouping multiple URL captures into one verification batch. Reuse the same id across related URL fetches; new id starts a new batch.

urlstring

Absolute URL (scheme://host/path) to fetch and snapshot for hypothesis verification.

cr_get_current_stateConvRadar (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...

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...

No parameter schema in public metadata yet.

cr_full_auditConvRadar (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-ste...2 params

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-ste...

Parameters* required

date_fromvalue

Inclusive start date in ISO YYYY-MM-DD format. Defaults to 30 days before today. Max window 90 days from date_to.

date_tovalue

Inclusive end date in ISO YYYY-MM-DD format. Defaults to today.

Readme

ConvRadar — Conversion Analyst inside Claude

Hosted MCP server that turns your Google Analytics 4 property into a conversation. Ask "where's my biggest funnel drop?" or "did mobile conversion drop last week?" in Claude, ChatGPT, Cursor or Cline — ConvRadar pulls the right slice, runs the diagnostic, and answers with numbers and a recommended action.

🌐 Website: https://convradar.com
💬 Chat with your GA4 in the browser: https://convradar.com/chat (email sign-in, free during the beta)
🔌 MCP endpoint: https://mcp.convradar.com/mcp
📧 Contact: https://convradar.com

This repository is the public manifest for the hosted ConvRadar MCP server. The server itself is a managed service — there is no self-hosted binary. Use the configuration below to connect any MCP-compatible client to it.

Screenshots

Live output from the connector — funnel audit on the demo tenant in Claude.ai, traffic-quality verdict in ChatGPT. Full set with paired prompts in media/.

View the full README on GitHub

Details

Repository: github.com/pikaivan/convradar-mcp
Website: convradar.com
Transport: HTTP
Registry: MCP registry, active