Install Umami MCP Server

Pick your client, copy the command, done.

Add it to Claude Code

claude mcp add umami-mcp-dac2 -- uvx --from git+https://github.com/lukasschmit/umami-mcp umami-mcp

Environment Variables

Set these before running Umami MCP Server.

VariableDescriptionRequired

UMAMI_URLBase URL for Umami instanceNo

UMAMI_API_KEYAPI key for Umami CloudNo

UMAMI_USERNAMELogin username for self-hostedNo

UMAMI_PASSWORDLogin password for self-hostedNo

UMAMI_CF_ACCESS_CLIENT_IDCloudflare Access service token client IDNo

UMAMI_CF_ACCESS_CLIENT_SECRETCloudflare Access service token secretNo

UMAMI_USER_AGENTCustom User-Agent for outbound requestsNo

UMAMI_DEBUGSet to 1/true to log outbound request URLsNo

Available Tools (5)

Once configured, Umami MCP Server gives your AI agent access to:

get_websitesList all tracked websites

get_statsSummary stats: pageviews, visitors, visits, bounces, totaltime

get_pageviewsTime-series pageview/session data

get_metricsBreakdown by type: path, url, entry, exit, referrer, domain, title, query, event, tag, hostname, browser, os, device, screen, language, country, region, city, channel

get_activeNumber of currently active visitors (last 5 minutes)

Try It Out

After setup, try these prompts with your AI agent:

→How many active visitors are currently on my website?

→Get the summary statistics for my main website for the last 7 days.

→Show me a breakdown of visitor countries for my website.

→What are the top performing pages on my site based on pageviews?

→List all the websites I have configured in my Umami account.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed

Conare · memory for coding agents

Keep this setup from going cold

Save the docs, env vars, and workflow around Umami MCP Server in Conare so Claude Code, Codex, and Cursor remember it next time.

Remember this setup$npx conare@latest

← Umami MCP Server overview Browse monitoring servers →