mcpbeat Sign in

Plausible Analytics MCP Server

local only

Plausible Analytics MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 917 installs a week from pypi. Last commit 28 Oct 2026.

Plausible Analytics MCP: privacy-first website stats, real-time visitors, breakdowns, and trends.

Installs per day peak 544 · avg 67 · +85% w/w
a month agotoday
917
Installs / week
pypi · plausible-mcp
0
Stars
0 open issues
28 Oct 2026
Last commit
from GitHub
MIT
License
Python

Nothing serious here today

Today is the operative word: we check Plausible Analytics MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add plausible-mcp -- uvx plausible-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "plausible-mcp": {
      "command": "uvx",
      "args": [
        "plausible-mcp"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.plausible-mcp]
command = "uvx"
args = ["plausible-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "plausible-mcp": {
      "command": "uvx",
      "args": [
        "plausible-mcp"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "plausible-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "plausible-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: PLAUSIBLE_API_KEY (Plausible Analytics API token), PLAUSIBLE_SITE_ID (Default Plausible site domain / ID (e.g. yourdomain.com)), PLAUSIBLE_BASE_URL (Custom self-hosted Plausible instance URL (default: https://plausible.io)).

Alternatives to Plausible Analytics MCP

same job, measured the same way
Plausible MCP by usefulapi
by usefulapi

Query site stats, realtime visitors, breakdowns and goals from Plausible Analytics.

8 tools answering
Pulse Analytics MCP server
by ciphera

Read-only web analytics from Pulse: your sites, totals, trends, breakdowns and realtime visitors.

answering
Cabin
by withcabin

Privacy-first, cookie-free web analytics. Read stats and manage sites from your AI.

answering
Eurolytics
by eurolytics

Privacy-first, cookie-free web analytics: create sites, install and verify tracking, read stats.

answering
DevDome Analytics
by devdome

Website traffic, bot reports, realtime visitors and site health for your DevDome sites

20 tools answering
Plausible MCP Server
by friendlygeorge

MCP server for Plausible Analytics — privacy-friendly web analytics. 12 tools for traffic, conver...

37 installs/wk local only
Measure.events Analytics
by meetclawdius

Privacy-first web analytics. Query pageviews, referrers, trends, and AI insights.

13 tools answering
Logly
by logly-uk

Query your Logly web analytics — traffic, funnels and real-time visitors — from any MCP client.

43 installs/wk local only

Plausible Analytics MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Plausible Analytics MCP?
Plausible Analytics MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package plausible-mcp was installed 917 times last week.
How do I connect Plausible Analytics MCP?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls plausible-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Plausible Analytics MCP?
The pypi package plausible-mcp was installed 917 times in the last week. Week over week that is +85%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Plausible Analytics MCP open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.