Plausible Analytics MCP Server
Enables AI assistants to query website statistics from Plausible Analytics, providing access to metrics like real-time visitors, traffic trends, and page performance. It supports both Plausible Cloud and self-hosted instances through the Stats API v2.
README
plausible-mcp
An MCP (Model Context Protocol) server for Plausible Analytics. Query your website stats directly from AI assistants like Claude.
Features
- Aggregate stats — visitors, pageviews, bounce rate, visit duration
- Time series — traffic trends by day, week, or month
- Breakdowns — top pages, traffic sources, countries, devices, browsers, and more
- Real-time visitors — current visitor count
- Site listing — discover all your Plausible sites
- Raw query — full access to the Plausible Stats API v2 for advanced use cases
Works with both Plausible Cloud and self-hosted instances.
Setup
1. Get a Plausible API key
Go to your Plausible account settings and create an API key.
2. Configure your MCP client
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"plausible": {
"command": "npx",
"args": ["-y", "plausible-mcp"],
"env": {
"PLAUSIBLE_API_KEY": "your-api-key-here"
}
}
}
}
Claude Code
claude mcp add plausible -- npx -y plausible-mcp
Then set the environment variable PLAUSIBLE_API_KEY in your shell.
Self-hosted Plausible
Add PLAUSIBLE_BASE_URL to point to your instance:
{
"env": {
"PLAUSIBLE_API_KEY": "your-api-key-here",
"PLAUSIBLE_BASE_URL": "https://plausible.example.com"
}
}
Tools
| Tool | Description |
|---|---|
list-sites |
List all sites in your Plausible account |
get-current-visitors |
Real-time visitor count for a site |
get-aggregate-stats |
Summary metrics over a time period |
get-timeseries |
Traffic trends over time (by day/week/month) |
get-breakdown |
Break down stats by dimension (pages, sources, countries, etc.) |
query |
Raw Plausible Stats API v2 query for advanced use cases |
Example prompts
- "How many visitors did example.com get this month?"
- "Show me traffic trends for the last 30 days"
- "What are my top 10 pages?"
- "Where is my traffic coming from?"
- "Compare this month's visitors to last month"
- "How many people are on my site right now?"
Environment variables
| Variable | Required | Default | Description |
|---|---|---|---|
PLAUSIBLE_API_KEY |
Yes | — | Your Plausible API key |
PLAUSIBLE_BASE_URL |
No | https://plausible.io |
Base URL for self-hosted instances |
Development
git clone https://github.com/Defilan/plausible-mcp.git
cd plausible-mcp
npm install
npm run build
To test locally:
PLAUSIBLE_API_KEY=your-key node dist/index.js
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.