Umami Analytics

v1.0.0Analyticsstable

Enables AI assistants to interact with Umami Analytics for both Cloud and self-hosted instances. It provides tools to retrieve website statistics, visitor metrics, pageview trends, and real-time active user counts.

analyticsclaudecursormcpmcp-server
Share:
18
Stars
0
Downloads
0
Weekly
0/5

What is Umami Analytics?

Umami Analytics is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to interact with umami analytics for both cloud and self-hosted instances. it provides tools to retrieve website statistics, visitor metrics, pageview trends, and real-time activ...

Enables AI assistants to interact with Umami Analytics for both Cloud and self-hosted instances. It provides tools to retrieve website statistics, visitor metrics, pageview trends, and real-time active user counts.

This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables AI assistants to interact with Umami Analytics for b

Use Cases

Retrieve website statistics and visitor metrics from Umami Analytics. Track pageview trends and active user counts. Analyze website analytics for cloud and self-hosted instances.
Macawls

Maintainer

LicenseMIT License
Languagego
Versionv1.0.0
UpdatedMay 10, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx umami-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Umami Analytics

The Umami MCP server enables AI assistants to query Umami Analytics instances — both Umami Cloud and self-hosted deployments — through the Model Context Protocol. It provides five tools covering website discovery, aggregated traffic statistics, time-series pageview data, dimensional breakdowns (pages, referrers, browsers, countries), and real-time active visitor counts. Product managers and developers can ask natural language questions about their site traffic without leaving their AI client.

Prerequisites

  • Go 1.21 or higher (if building from source), or a prebuilt binary from the releases page
  • A running Umami Analytics instance (cloud or self-hosted)
  • UMAMI_URL and either UMAMI_API_KEY (cloud) or UMAMI_USERNAME and UMAMI_SECRET_KEY (self-hosted)
  • An MCP client such as Claude Desktop, Cursor, or Claude Code
1

Install the server binary

Install the umami-mcp-server binary via go install. It will be placed in ~/go/bin/.

go install github.com/Macawls/umami-mcp-server@latest
2

Set environment variables

Export your Umami instance URL and credentials. Use UMAMI_API_KEY for Umami Cloud or UMAMI_USERNAME and UMAMI_SECRET_KEY for self-hosted.

export UMAMI_URL=https://your-umami-instance.com
# For Umami Cloud:
export UMAMI_API_KEY=your_api_key
# For self-hosted:
export UMAMI_USERNAME=admin
export UMAMI_SECRET_KEY=your_password
3

Test the binary

Run the server manually to confirm it starts and can reach your Umami instance.

~/go/bin/umami-mcp-server
4

Add the server to your MCP client config

Register the binary with your MCP client, passing credentials via environment variables.

5

Optional: use a config.yaml file

Place a config.yaml alongside the binary with equivalent YAML keys as an alternative to environment variables.

umami_url: "https://your-umami-instance.com"
umami_api_key: "your_api_key"
umami_team_id: "optional_team_id"

Umami Analytics Examples

Client configuration

Add this block to claude_desktop_config.json. Replace the binary path and env values with your actual setup.

{
  "mcpServers": {
    "umami": {
      "command": "/Users/you/go/bin/umami-mcp-server",
      "args": [],
      "env": {
        "UMAMI_URL": "https://your-umami-instance.com",
        "UMAMI_API_KEY": "your_api_key"
      }
    }
  }
}

Prompts to try

Prompts that use get_stats, get_pageviews, get_metrics, and get_active tools.

- "How many visitors did my website get last week?"
- "Show me a breakdown of my top 10 pages by pageviews this month"
- "Where are my visitors coming from? Break it down by country"
- "How many people are actively on my website right now?"
- "Which referrers sent the most traffic to my site in the last 30 days?"

Troubleshooting Umami Analytics

Connection refused or 401 Unauthorized from Umami

Verify UMAMI_URL points to your running instance (include https:// and no trailing slash). For cloud, confirm the UMAMI_API_KEY is valid. For self-hosted, check username and password.

go install fails: command not found

Ensure Go 1.21+ is installed and ~/go/bin is in your PATH. Run 'go version' to verify, then add 'export PATH=$PATH:~/go/bin' to your shell profile.

get_websites returns an empty list

If you use team-based access in Umami, set the UMAMI_TEAM_ID environment variable. Without it, the server may not see websites scoped to your team.

Frequently Asked Questions about Umami Analytics

What is Umami Analytics?

Umami Analytics is a Model Context Protocol (MCP) server that enables ai assistants to interact with umami analytics for both cloud and self-hosted instances. it provides tools to retrieve website statistics, visitor metrics, pageview trends, and real-time active user counts. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Umami Analytics?

Follow the installation instructions on the Umami Analytics GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Umami Analytics?

Umami Analytics works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Umami Analytics free to use?

Yes, Umami Analytics is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Analytics MCP Servers

Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "umami-mcp-server": { "command": "npx", "args": ["-y", "umami-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Umami Analytics?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides