What are the prerequisites to run the server?
You need to install `uv` and have Umami account credentials: API URL, username, password, and team ID.
@MCP-Mirror
Basic information
Mirror of
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"
}
}
}
}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
A Model Context Protocol (MCP) server that enhances Claude with access to website analytics data from Umami. It enables Claude to analyze user behavior, track website performance, and generate data-driven insights.
Install uv, then add the MCP server configuration to your Claude Desktop config file (claude_desktop_config.json) with the Umami API URL, username, password, and team ID. When you open Claude Desktop, the server connects automatically. Use the built-in "Create Dashboard Prompt" or interact via natural language; Claude will choose the appropriate tools.
You need to install `uv` and have Umami account credentials: API URL, username, password, and team ID.
Add a JSON entry under `mcpServers` in your `claude_desktop_config.json`, specifying `uv` as the command and the required environment variables (`UMAMI_API_URL`, `UMAMI_USERNAME`, `UMAMI_PASSWORD`, `UMAMI_TEAM_ID`).
Yes, define a prompt structure in `list_prompts()` and implement its logic in `get_prompt()` within `src/analytics_service/server.py`.
The `get_docs` tool chunks journey data, embeds them with a sentence transformer, and returns only the most relevant segments via semantic search, preventing context window overload.
HasData's hosted Zillow MCP server lets AI agents search homes for sale, rentals and sold listings, then retrieve property details, price history and Zillow estimates as structured JSON.

Building permit data and Florida contractor license checks over MCP. 81.8M permit records from the cities and counties that issue them, across 51 states. Four tools: verify_license, search_permits, lookup_contractor, roo
Find and enrich people from 750M professional profiles, with Next Move Signal job-change scores.
Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.

App Store and Google Play data for agents: apps, reviews, keyword research, top charts, competitors and ASO audits.
Comments