Amami
QuestionsInstallMCP toolsSecurity
Start Now

Analytics for AI-native teams

Analytics answers, inside the AI tools your team already uses.

Amami connects your approved MCP client to Umami, so your team can ask clear questions about traffic, pages, visitors, and referrers without context switching.

Start now View setup guide
  • Browser authorization
  • Local client configuration
  • Read-only analytics access
AmamiAnalytics assistant
Connected

What changed in our traffic this week?

Visitors6,952+18.4%
Top page/pricing1,204 views
Leading sourceGoogle29% of traffic
Summary

Visitors increased, led by organic search. The pricing page received the largest share of attention. Compare it with the previous period to decide what to review.

Answers that stay close to the data.

Ask a direct question, then inspect the underlying Umami metrics.

Traffic summary

> "How was traffic last week?"

"I can read visits, pageviews, bounces, and time on site for the selected period, then summarize what changed."

Top pages

> "Which pages performed best this month?"

"I can compare the pages receiving attention and keep the underlying metrics in the response for you to inspect."

Traffic sources

> "Where did visitors come from?"

"I can group referrers and countries from your Umami data, then point out the changes worth investigating."

One maintained setup guide for every MCP client.

Authorize in your browser, register the active client, then verify without test data.

Copy this prompt and send it to your AI:

Read and follow the canonical Amami MCP and Skills installation guide at https://analytics.amami.dev/install/mcp-install.md. Use this guide as the only setup source. Do not use web search or another installation guide.

Install, authorize, then verify.

The canonical guide installs MCP and Amami Skills, checks Node.js, runs browser setup, registers your active MCP client, and verifies access without creating websites or sending events. Login, registration, and authorization stay in your browser, under your control.

  • Canonical MCP and Skills installation guide
  • Client-specific registration
  • Browser-based user authorization

What your AI can do once connected.

Six focused analytics reads, designed for natural-language questions.

List websites

Find the Umami sites your assistant is allowed to analyze.

Read traffic stats

Pull visitors, pageviews, visits, bounces, and time on site.

Inspect trends

Read traffic patterns by day or hour for the period you choose.

Find top pages

See which pages are receiving attention.

Check active visitors

Read the current active-visitor count.

Trace traffic sources

Inspect where visitors came from.

Local, authorized, and scoped.

Your agent can inspect analytics. You retain control of credentials and authorization.

Browser consent stays with you

Login, registration, and MCP authorization happen in your browser. Your agent does not perform them for you.

Credentials stay in local configuration

Your API key is stored by your MCP client on your machine, rather than supplied to an AI conversation.

Scoped verification

Setup enables the approved client scope. Verification only checks your account, website list, and available tools without creating test data.

Keep the dashboard

Amami is an AI-native read layer for Umami, not a dashboard or BI replacement.

Secure
Private
Scoped
Local Keys
Amami

© 2026 Amami. Analytics for AI coding assistants.

DocsMCP GitHubSkills