Vitrus analytics
Read-only analytics for all your apps: users, AI traffic, revenue, with the SQL behind every number.
Connector by vitrus.devOfficial · Domain verified by the MCP Registry
Chalk Labs
Need help deploying Vitrus analytics?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install connector/vitrus-dev-analytics
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Remote endpoint
https://app.vitrus.dev/mcpRemote (HTTP)
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 14 read · 0 write · 0 delete · 3 not yet classified
- Secrets
- None asked for
- Install scripts
- Nothing to install (hosted)
- Runs as
- Hosted (remote endpoint)
Tools by what they do 17
Read from the source code; the running server may list different tools.
Read 14 · Look things up without changing anything.
get_ai_trafficget_digestget_errorsget_journeysget_overviewget_portfolioget_realtimeget_retentionget_revenueget_tracking_snippetget_web_vitalslist_goals
Show 2 more tools
list_sitesquery_stats
Not yet classified 3 · We could not tell from the name and description.
analyze_funnelget_lifecyclegoal_report
Network hosts it talks to 1
app.vitrus.dev· found in remote endpoint, install command
Tools (17)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
analyze_funnelOrdered conversion funnel. Steps are counted IN ORDER: a step only counts if it happened after the previous one, so someone who signs up and then visits the pricing page is not a conversion. Omit 'steps' to use the site's default funnel.
get_ai_trafficTraffic from AI assistants, kept separate from AI crawlers. 'AI referral' is a human who arrived from ChatGPT/Perplexity/Claude; 'AI crawler' is GPTBot or ClaudeBot READING the site and bringing nobody. Crawlers are never counted as visitors. Also returns which pages the crawlers read — the only real feedback loop for GEO/AEO work.
get_digestThe plain-language summary for a period: what happened, what changed, what to do. Every sentence lists the evidence ids it rests on. This text is generated deterministically from queries, not by a language model — you can quote it safely.
get_errorsJavaScript errors captured from real visits, grouped by message and page, with the browsers they occur in. Stack traces are never collected (they leak user data), so expect message, file and line only.
get_journeysUser journeysThe most common page paths through the site, in order (a Sankey's data). Optionally pin steps: stepFilters[i] is an exact path or a pattern with * for step i.
get_lifecycleUser lifecycleSigned-in users, counted — never listed: active, new, retained, came back, lost (churned) versus the previous period of equal length, quick ratio, one-and-done rate, current plans, who became paying and who stopped. Needs vitrus.identify(user.id) on the site; the id is hashed in the browser and again on the server, so no email or name exists to return. Each number comes with its query.
get_overviewTraffic overview for a site: visitors, sessions, pageviews, bounce rate, visit duration, channels, top pages and referrers. EVERY metric comes back with the SQL that produced it, its parameters and the raw rows — cite or verify them rather than trusting the number alone.
get_portfolioPortfolio: all sitesEvery site you can read in one table: visitors (with the previous period), active and new users, lost users, signups, became paying, paying users and revenue per currency, plus totals. Counts are added across sites — identities are hashed per site, so the same person on two sites counts twice, by design.
get_realtimeWho is on the site nowLive: people seen in the last 5 minutes, and the pages they are on and where they came from. Humans only (bots and AI crawlers excluded). Each figure comes with its query.
get_retentionCohort retention matrix. IMPORTANT: this returns available=false for anonymous traffic and explains why — visitor ids rotate daily (no cookies), so cross-day tracking is mathematically impossible without vitrus.identify(). Do not report a retention number when available=false.
get_revenueRevenueRevenue from events that carry revenue + currency: totals, orders, average order value, revenue per visitor, conversion rate, and a breakdown. Per currency — amounts are NEVER converted between currencies. Acquisition dimensions (channel, source, campaign) are where the visit began, not the checkout page.
get_tracking_snippetInstall snippetThe script tag to add to the site's <head>, and how to send custom events and revenue.
get_web_vitalsCore Web Vitals from real visits (p75, not average — a few slow visits drag an average and hide the problem), plus the slowest pages by LCP.
goal_reportGoal conversionsConversions and conversion rate for the site's saved goals — or for goals you pass in. A conversion is a session that reached the goal at least once; the rate is over all sessions in the range. Each comes with its query.
list_goalsSaved goalsThe goals saved for a site (page patterns or custom events). Use goal_report for their conversions.
Show 2 more tools
list_sitesList the sites this caller can read. Returns id, name, domain and privacy mode. Start here when you do not already have a site id.
query_statsFlexible stats queryThe general query: one metric (visitors, sessions, pageviews or events), optionally broken down by a dimension (path, channel, source, referrer_host, country, city, device, browser, os, utm_*, event, …) or by 'day' for a time series, with optional filters and an exact date range. Returns the rows AND the SQL that produced them. Use this for anything the dedicated tools do not answer.
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit
- Oct 23, 2026 (7 days ago)
- Last release
- Oct 18, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
dev.vitrus/analytics- Version
- 0.11.1
- Auth
- Auth not stated
- License
- Apache-2.0
- Repository
- github.com/Vitrus-Dev/vitrus
- Website
- vitrus.dev/docs/mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Vitrus analytics running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Vitrus analytics MCP server. Agent Mart. https://agentmart.dev/connectors/vitrus-dev-analytics (last updated 2026-10-24)