Umami Analytics MCP Server

@jakeyShakey

About Umami Analytics MCP Server

No overview available yet

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "analytics_service": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/analytics_service",
        "run",
        "analytics-service"
      ],
      "env": {
        "UMAMI_API_URL": "https://example.com",
        "UMAMI_USERNAME": "yourUmamiUsername",
        "UMAMI_PASSWORD": "yourUmamiPassword",
        "UMAMI_TEAM_ID": "yourUmamiTeamId"
      }
    }
  }
}

Tools

Retrieve a list of websites and their IDs in your Umami account

Get key metrics like pageviews, visitors, bounce rate for a website

Analyze specific metrics like URLs, referrers, browsers, countries

Get time-series pageview data with customizable intervals

Monitor current number of active visitors on a website

Retrieve session IDs for specific events or time periods

Get detailed activity data for a specific session ID

Perform semantic search on many user journeys, returning the most relevant chunks for a given question

Capture visual snapshots of webpages

Retrieve and analyze webpage HTML source code

Overview

What is Umami Analytics MCP Server?

An MCP server that gives Claude access to Umami website analytics data, enabling analysis of user behavior, website performance, and data-driven insights. It connects to your Umami platform (self-hosted or Umami Cloud) and provides tools for retrieving metrics, tracking visitors, capturing screenshots, and analyzing page content.

How to use Umami Analytics MCP Server?

Configure Claude Desktop with the analytics_service MCP server entry pointing to your local copy of the server, supplying UMAMI_API_URL, UMAMI_USERNAME, UMAMI_PASSWORD, and UMAMI_TEAM_ID. After starting Claude Desktop, 10 tools become available. Use the built-in “Create Dashboard Prompt” or natural language requests to have Claude analyze your data.

Key features of Umami Analytics MCP Server

Retrieve website list and IDs from your Umami account
Get key metrics: pageviews, visitors, bounce rate
Analyze metrics by URL, referrer, browser, country
View time-series pageview data with customizable intervals
Monitor real‑time active visitors on a website
Retrieve session IDs and detailed tracking data
Semantic search over user journeys (embedding + chunking)
Capture webpage screenshots and HTML source code via Crawl4AI

Use cases of Umami Analytics MCP Server

Ask Claude to build a visual dashboard of your website analytics
Analyze user journeys to identify pain points and drop‑off areas
Monitor current visitor activity and compare with historical trends
Get performance recommendations enriched with live page screenshots
Automate recurring analytics reports using custom prompts

FAQ from Umami Analytics MCP Server

What tools does the server provide?

The server provides 10 tools: get_websites, get_website_stats, get_website_metrics, get_pageview_series, get_active_visitors, get_session_ids, get_tracking_data, get_docs, get_screenshot, and get_html.

What are the prerequisites and runtime requirements?

You need uv installed (pip install uv). The server runs locally via uv and connects to your Umami instance (self‑hosted or Umami Cloud). It also uses the open‑source Crawl4AI web crawler for screenshots and HTML retrieval.

Where does analytics data live?

All analytics data stays in your Umami instance. The server queries the Umami API and does not store any data. User journeys are temporarily embedded and searched in memory (using a Hugging Face sentence transformer) to avoid context window issues.

Are there any known limits?

Screenshots are downsampled to reduce size and avoid context window limits. The get_docs tool performs semantic search on chunked user journeys to keep token usage low.

What transports and authentication does the server use?

The server uses standard MCP transport (stdio) via the uv command. Authentication is handled by supplying Umami credentials (UMAMI_USERNAME, UMAMI_PASSWORD) and a team ID in the environment variables.

Frequently asked questions

What tools does the server provide?

The server provides 10 tools: `get_websites`, `get_website_stats`, `get_website_metrics`, `get_pageview_series`, `get_active_visitors`, `get_session_ids`, `get_tracking_data`, `get_docs`, `get_screenshot`, and `get_html`.

What are the prerequisites and runtime requirements?

You need `uv` installed (`pip install uv`). The server runs locally via `uv` and connects to your Umami instance (self‑hosted or Umami Cloud). It also uses the open‑source Crawl4AI web crawler for screenshots and HTML retrieval.

Where does analytics data live?

Are there any known limits?

Screenshots are downsampled to reduce size and avoid context window limits. The `get_docs` tool performs semantic search on chunked user journeys to keep token usage low.

What transports and authentication does the server use?

The server uses standard MCP transport (stdio) via the `uv` command. Authentication is handled by supplying Umami credentials (`UMAMI_USERNAME`, `UMAMI_PASSWORD`) and a team ID in the environment variables.

Comments

Basic information

More Data & Analytics MCP servers

🪐✨ Jupyter MCP Server

datalayer

🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.

1.2K

MCP.science: Open Source MCP Servers for Scientific Research 🔍📚

pathintegral-institute

Open Source MCP Servers for Scientific Research

142

Linkly Link Shortener

Linkly

Linkly is an URL shortener with geo redirects, click & conversion tracking, link rotators, mobile deep links and an URL shortening API.

Opinly

Track competitors, rankings, and how AI answers rank you — then write and publish the fix.

Subtext

Subtext by Fullstory

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can