Privacy friendly, cookieless web analytics built MCP-first. "Add analytics to my
Privacy friendly, cookieless web analytics built MCP-first. "Add analytics to my Next.js app" → an AI agent runs the setup_analytics_for_site tool, picks the right install snippet, edits your layout file, and verifies the script is loading. OAuth onboarding, no API keys to paste.
active Production-safe Score 89/100 http no auth
At a glance
| Endpoint | https://gizmoanalytics.io/mcp |
|---|---|
| Source | https://glama.ai/mcp/servers/l799jrwpam |
| Transport | http |
| Tools | 39 |
| Auth | none |
| First seen | 2026-06-20 06:08:39 |
| Last checked | 2026-11-17 21:35:06 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 855 / 1516 ms |
| Last successful check | 2026-11-17 21:35:06 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (39)
summarize_all_sites— Workspace-wide status rollup: fleet totals with % change vs prior period, per-site status, prioritized needs-attention list, top movers, AI-rank_sites_by_growth— Ranks sites by signed % visitor change vs the prior period. Sites under 20 visitors in either period are excluded as noise (count in excludeidentify_dead_sites— Finds abandoned sites: 'never_installed' (tracker likely never added) or 'went_silent' (had traffic, quiet for N+ days). Sorted never_instaldetect_anomalies— Flags days with unusual traffic per site via z-score over the range. Sites under 20 total visitors are skipped as low-signal. Omit site_id texplain_traffic_change— Explains why traffic on a site changed: overview deltas, top page and referrer gainers/losers vs prior period, anomaly-day callouts, and theget_realtime— Live activity over the last 5 minutes: active visitors, pageviews, custom events, latest observed pages and recent actions. Excludes bots. Pget_conversion_report— Audit conversion measurement for a site: goal rates with visitor denominators, funnel completion rates, transitions ranked by lost sessions,setup_analytics_for_site— One-call install workflow: creates the site and returns the install snippet, the exact file to paste it into (paste_target.file), and next slist_sites— Lists every site in the workspace with id, domain, createdAt, and ignored status. Use the returned site.id for other site-scoped tools.create_site— Registers a domain and returns the install snippet, a privacy_policy reminder, and an optional badge. For a full install workflow prefer setget_install_snippet— Re-fetches the framework-specific install snippet for an existing site — for a switched framework or a snippet never installed. Edit the tarverify_install— Fetches the site's homepage and checks for the tracker script. Returns installed:true, installed:false with a reason (usually not deployed yget_badge_snippet— Returns the "Powered by Gizmo" footer badge as a single anchor tag. Place inline in the existing footer next to the copyright line; don't wrget_event_tracking_snippet— Returns the JS snippet for firing a custom event (e.g. window.gizmo("signup", {plan:"pro"})). Requires the tracker already installed. Edit tadd_site_tags— Attaches one or more free-form tags to a site, creating new tags as needed. Pair with filter_sites_by_tag to drill into a group.filter_sites_by_tag— List sites carrying a tag. Identical to list_sites({tag}).create_goal— Creates a conversion goal for a site (path-prefix or named custom event). Shows on the site dashboard with conversion count + rate.list_goals— Lists every goal for a site with conversion count and rate over the date range. Requires create_goal first if none exist.delete_goal— Removes a conversion goal and its historical data. Destructive — confirm first.create_funnel— Creates an ordered multi-step funnel for a site. A session reaches step N if it matched steps 0..N in the same session (30-min idle gap).list_funnels— Lists every funnel for a site with per-step reached counts and drop-off rate. Requires create_funnel first if none exist.delete_funnel— Removes a funnel by id. Destructive — confirm first.rename_event— Renames an event on a site: backfills every past event to the new name, updates any goal/funnel that targets the old name, and — going forwalist_event_renames— Lists every configured event rename for a site.get_workspace_overview— Aggregate metrics across all sites in the workspace: visitors, pageviews, sessions, bounce rate, top sites.get_site_traffic— Traffic metrics for a single site: overview, top pages, top referrers.get_revenue— Revenue attributed to traffic from the site's payment provider: totals (revenue, payments, customers, recurring share) plus a first-touch brconnect_payment_provider— Step 1 of revenue-attribution setup: creates or fetches a site's payment integration and returns the webhook URL and events to enable. Idempset_payment_api_key— Zero-code Stripe revenue setup: saves a read-only restricted API key for an integration from connect_payment_provider, imports the last 90 dset_payment_webhook_secret— Step 2 of revenue-attribution setup: saves the webhook signing secret for an integration from connect_payment_provider, activating revenue iget_top_pages— Top page paths by event count, optionally scoped to one site.get_scroll_depth— Page-level scroll engagement for one site: average furthest visible percentage and measured-pageview count. Snapshots of each pageview countget_top_referrers— Top referrer hostnames by event count, optionally scoped to one site.get_breakdown— Top-N rows for one built-in dimension (page, referrer, country, region, city, browser, device, language, screen, channel, ai_source, hostnamquery_events— Queries raw events. Defaults to the latest 100, max 1000 per call; paginate large analyses via date_range.get_time_series— Time-bucketed visitors/pageviews/events, one row per bucket. Bucket auto-resolves to hour for windows ≤48h, day otherwise.breakdown_by_property— Top values for a custom event property (instrumented via get_event_tracking_snippet), with visitor counts. For built-in dimensions use get_blist_metrics— List custom metrics pushed to this workspace (server health, queue depth, business numbers) with each series' tags and latest value. Start hquery_metrics— History and latest value of one custom metric, one line per tag set. Use for questions like 'how much disk is left?' (read latest) or 'how d
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:35:06 | ✓ | ✓ | 463 ms | 90 | active |
| 2026-11-17 20:53:33 | ✓ | ✓ | 598 ms | 90 | active |
| 2026-11-17 20:26:28 | ✓ | ✓ | 401 ms | 90 | active |
| 2026-11-17 19:41:44 | ✓ | ✓ | 436 ms | 90 | active |
| 2026-11-17 19:00:23 | ✓ | ✓ | 513 ms | 90 | active |
| 2026-11-17 18:35:43 | ✓ | ✓ | 660 ms | 90 | active |
| 2026-11-17 17:56:05 | ✓ | ✓ | 459 ms | 90 | active |
| 2026-11-17 17:26:58 | ✓ | ✓ | 506 ms | 90 | active |
| 2026-11-17 16:41:39 | ✓ | ✓ | 341 ms | 90 | active |
| 2026-11-17 15:55:19 | ✓ | ✓ | 619 ms | 90 | active |
| 2026-11-17 14:57:02 | ✓ | ✓ | 585 ms | 90 | active |
| 2026-11-17 14:26:52 | ✓ | ✓ | 880 ms | 90 | active |
| 2026-11-17 13:41:19 | ✓ | ✓ | 638 ms | 90 | active |
| 2026-11-17 13:12:31 | ✓ | ✓ | 627 ms | 90 | active |
| 2026-11-17 12:40:50 | ✓ | ✓ | 557 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://gizmoanalytics.io/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/gizmoanalytics-io-mcp # JSON