Computes funnel analysis to measure drop-offs and conversions across key steps in a user journey. Analyzes conversion rates, drop-off points, and time to completion across up to 32 steps.

Computes impact quantification analysis comparing conversion performance between segments. Provides metrics including conversion rates, bounce rates, session time, pageviews, and revenue impact with statistical significance testing.

Computes user navigation journeys, visualizing how visitors navigate your site. Provides hierarchical tree structure showing common paths, drop-off points, and navigation patterns. Supports forward (from landing pages) and reverse (from exit pages) analysis up to 7 steps.

Computes page comparison analysis comparing key performance metrics across multiple page groups (2-10). Provides metrics: views, bounce rate, exit rate, scroll rate, time spent, activity level, load times, and conversion rates.

Compute page metrics, at the page group level. Use it to get an overview of the performance of the fraction of the website.

Computes aggregated metrics across the entire website. Returns data grouped by specified dimensions (device, date, browser, country, etc.). Filters: time period (startDateTime/endDateTime), device type (DESKTOP/MOBILE/TABLET/ALL), conversion goals (goalId), or advanced user filters (userFilter for browsers, goals, segments, page interactions). Use dimensions parameter to group results. Defaults to no grouping if not specified.

Retrieve all page groups for a specific mapping, sorted alphabetically by name.

Get top errors ranked by impact on conversion goals. Shows business-critical errors affecting revenue and conversions. USE for: business impact analysis, revenue-critical issues, prioritizing fixes by business value, conversion impact of errors. Requires mappingId and goalId to analyze goal-specific impact.

Get top errors ranked by missed business opportunities (eCommerce focused). Shows revenue impact of errors. USE for: eCommerce missed revenue opportunities, lost sales analysis, revenue impact of errors. Always uses goalId -1 for eCommerce analysis. Requires mappingId.

Get top errors ranked by sessions with errors. Main widget for general error analysis showing error trends, rates, and most frequent errors. USE for: general error questions, error trends, most frequent errors, volume comparisons, overall error patterns. This is the primary tool for error analysis.

Get page groups ranked by lost conversions due to errors. Shows business impact of errors by page groups. USE for: page group impact analysis, page-level conversions, top pages losing conversions, business impact by page groups. Requires mappingId and goalId to analyze conversion impact.

Get pages most affected by errors in a scatter plot comparing error volume with page traffic. USE for: identifying pages most affected by technical issues, development resource focus, scatter plot analysis of pages vs error rates. Supports both 'pagegroups' (default) for category-level analysis and 'pages' for detailed URL-level analysis. Requires mappingId parameter.

Returns a list of projects (id and name) accessible to the user

Recommend goals based on user engagement and usage frequency (how often goals are viewed, used in analyses, etc.) within the platform.

Recommend mappings based on user engagement and usage frequency (how often mappings are viewed, used in analyses, etc.) within the platform.

Recommend page groups based on user engagement and usage frequency (how often page groups are viewed, used in analyses, etc.) within the platform.

Recommend segments based on user engagement and usage frequency (how often segments are viewed, used in analyses, etc.) within the platform. A project with no recent engagement data falls back to the most recently updated segments instead. - This tool cannot page. When `total` exceeds `returned`, raise `limit` instead

Search and retrieve goals for a project.

Search and retrieve mappings for a project.

Search and retrieve segments for a project, optionally filtered by name. - To find a segment by name, pass `text` rather than listing segments and scanning the result: the filter is applied before any row limit, so a filtered answer is complete even on a project too large to list. Pass one contiguous fragment of the name, not several words that may not be adjacent - NEVER describe a segment list as complete unless `offset` plus `returned` equals `total` — on a single call `offset` is 0, and while paging it is the position of the page in hand. `returned` counts one page, so on its own it reaches `total` only when the whole list fits in one - When a response carries `nextOffset`, pass it back as `offset` to read the next page; its absence means no further page can be read — which is not the same as having reached `total` - Every page of a large project costs a full read of it, so do not walk one in default-sized pages: narrow with `text` where the task allows it, and where the whole list is genuinely needed raise `limit` so it arrives in as few calls as possible

Submit feedback about your MCP server experience. Help us improve by rating tools and sharing your thoughts!