Umami Compass MCP server

Read from the package source without running it. The installed server may list more.

• analyze_performance_portfolio

  Compare Core Web Vitals across a bounded website portfolio with compact-by-default output, metric-specific drill-down selection, confidence, event/pageview ratios, and precise section truncation metadata.

• analyze_release_impact

  Compare equal pre- and post-release windows across traffic breakdowns and Core Web Vitals. Returns a compact executive summary by default; request full detail for drill-down evidence. Recent releases use a partial post window and an equally shortened pre window.

• compare_performance_breakdown

  Align page, page-title, device or browser rows across two periods. Comparable rows come first; undersized rows are excluded by default and missing capped candidates remain unknown rather than being treated as zero.

• compare_traffic_series

  Return aligned current and comparison traffic buckets to locate the exact day or hour when traffic changed.

• compare_web_vitals

  Compare all five Web Vital p75 summaries against a previous, year-over-year or custom period with ratings, materiality, event-count readiness and explicit filter scope.

• explain_traffic_change

  Compare traffic with a previous, year-over-year, or custom period and rank observed changes across pages, referrers, countries, devices, channels, and events. Results describe association, not causation.

• get_active_visitors

  Get the current number of active visitors for a website.

• get_event_series

  Get custom-event counts over time, optionally filtered to a named event.

• get_event_stats

  Get aggregate custom-event statistics and comparison values.

• get_heatmap

  Get Umami 3.2 click or scroll heatmap data. Successful responses state whether data is available and why an authorized result is empty. Omit urlPath to list pages; provide it for bounded detail.

• get_metrics

  Get a ranked aggregate Umami metric breakdown such as paths, referrers, countries, devices, events, channels or URLs. Visitor identifiers are excluded from the core toolset.

• get_pageviews

  Get Umami 3.2 pageview and session time series. Both arrays are preserved in the response.

• get_performance_breakdown

  Rank Web Vital percentiles by page, page title, device or browser. Rows default to 20 performance events and report the upstream limitation that per-metric non-null counts are unavailable.

• get_performance_cross_tab

  Derive a bounded two-dimensional performance breakdown through explicit fan-out. Candidate source, request count, sample limitations and truncation are reported so the result is not mistaken for a native exhaustive pivot.

• get_portfolio_overview

  Summarize bounded aggregate traffic across visible websites, including period changes, growth and decline leaders, stale tracking, failures, and suspicious jumps.

• get_revenue_metrics

  Break down Umami 3.2 revenue by country, region, referrer or channel.

• get_revenue_stats

  Get Umami 3.2 revenue totals and comparison values in a chosen currency.

• get_route_group_performance

  Measure caller-defined route templates with exact regex-filtered performance queries instead of attempting to merge non-composable percentiles from individual URLs.

• get_saved_report

  Get one saved report definition. The website ID is required to enforce the local allowlist and is verified against the response.

• get_server_info

  Get the local package version, enabled toolsets, safety limits, and supported analysis capabilities without exposing credentials.

• get_session

  Get metadata for one Umami visitor session.

• get_session_activity

  Get a bounded list of pageviews and events that occurred during one session and time range.

• get_session_stats

  Get aggregate session metrics for a website and time range.

• get_web_vitals

  Get normalized Umami 3.2 LCP, INP, CLS, FCP and TTFB summaries plus a bounded series for one metric. Empty data, partial buckets, filter scope and unavailable upstream sample counts are explicit.

• get_website

  Get metadata for one website.

• get_website_date_range

  Get the earliest and latest analytics timestamps available for a website.

• get_website_stats

  Get visits, visitors, pageviews, bounces, visit duration and Umami's comparison values for a time range.

• list_events

  List and search custom events for a website and time range.

• list_replays

  List Umami 3.2 session replay metadata. Successful responses state whether data is available and why an authorized result is empty. Raw rrweb event payloads are intentionally excluded.

• list_saved_reports

  List saved report definitions for one website without modifying them.

• list_segments

  List reusable website segments or cohorts from Umami's paged response with explicit context limits.

• list_sessions

  List and search visitor sessions for a website and time range.

• list_websites

  List websites visible directly or through any team membership of the configured Umami identity. If UMAMI_WEBSITE_IDS is set, returns only that exact allowlist.

• resolve_website

  Resolve a website UUID from a UUID, domain, URL, or website name. Ambiguous matches return bounded candidates instead of guessing.

• run_attribution_reportwrite action

  Calculate first-click or last-click attribution for a conversion path or event with bounded channel arrays.

• run_breakdown_reportwrite action

  Cross-tabulate up to three Umami dimensions, including derived channel combinations, and return the highest-ranked bounded rows.

• run_funnel_reportwrite action

  Calculate a 2–8 step Umami funnel. windowMinutes controls the allowed time between consecutive steps.

• run_goal_reportwrite action

  Calculate an Umami conversion goal for a path or custom event.

• run_journey_reportwrite action

  Calculate the most common 2–7 step user journeys and return a bounded ranking.

• run_retention_reportwrite action

  Calculate daily Umami cohort retention and return a bounded result set.

• run_utm_reportwrite action

  Calculate Umami source, medium, campaign, term and content performance with bounded category arrays.

• tracking_health_check

  Audit visible websites for stale or missing traffic, traffic drops, domain mismatches, referral-spam patterns, custom-event availability, recorder configuration, and section permission failures. Disabled optional features are warnings only when marked as expected.

• Code scan58 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 8 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

83/100

higher than 65% of 48,255 servers

Tools

42

the typical server has 7

Tools that change things

17%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

40

more than 31% of 12,191 servers with a package

Umami Compass: common questions

Is Umami Compass MCP server safe?

Mostly: it is graded B (83/100). Read the Umami Compass safety report

How do I install Umami Compass?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Umami Compass need an API key?

Yes. The registry entry asks for UMAMI_API_KEY, UMAMI_ACCESS_TOKEN, UMAMI_PASSWORD.

Is Umami Compass maintained?

The last commit was 48 days ago (2026-09-17). The latest release is v0.5.1.

How does Umami Compass compare with other MCP servers?

safety score 83/100 (higher than 65% of 48,255 servers); tools 42 (the typical server has 7); tools that change things 17% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.