Skip to main content
Glama
Logly MCP server

Logly MCP server

Official
by logly-uk

Logly MCP server

Query your Logly web analytics from Claude, Cursor, or any Model Context Protocol client.

Logly is privacy-first web analytics — under 1 KB, cookie-free, GDPR compliant by design. This server exposes your analytics over MCP so an AI assistant can answer questions like "how did traffic change this week?" or "where is my signup funnel losing people?" — and even hand you the install snippet for a new site.

Requirements

  • Node.js 18 or newer

  • A Logly account and an API key — create one in Settings → API keys in your Logly dashboard. The key looks like logly_a1b2c3... and is shown only once.

Related MCP server: rybbit-mcp

Setup

The server runs via npx — no install step needed.

Claude Desktop

Edit claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "logly": {
      "command": "npx",
      "args": ["-y", "@logly-uk/mcp"],
      "env": { "LOGLY_API_KEY": "logly_your_key_here" }
    }
  }
}

Restart Claude Desktop.

Claude Code

claude mcp add logly -e LOGLY_API_KEY=logly_your_key_here -- npx -y @logly-uk/mcp

Cursor

Add to .cursor/mcp.json in your project (or the global one):

{
  "mcpServers": {
    "logly": {
      "command": "npx",
      "args": ["-y", "@logly-uk/mcp"],
      "env": { "LOGLY_API_KEY": "logly_your_key_here" }
    }
  }
}

Tools

Tool

What it does

logly_list_sites

List every site in your account with its site ID — start here.

logly_stats

Pageviews, sessions, visitors, bounce rate, avg duration, daily series, previous-period comparison.

logly_breakdown

Top pages, referrers, countries and device/browser split.

logly_realtime

Visitors active right now.

logly_events

Custom event counts.

logly_funnels

List a site's conversion funnels and their steps.

logly_funnel_results

Completion counts and drop-off per funnel step.

logly_install_snippet

The <script> tag to add Logly to a site's <head>.

Date filters

Stats tools accept a days window (7, 30 or 90 — defaults to 30) or an explicit from / to pair (YYYY-MM-DD). If both are given, from/to wins.

Environment variables

Variable

Required

Purpose

LOGLY_API_KEY

yes

Your Logly API key.

LOGLY_API_BASE

no

Override the API base URL (default https://app.logly.uk).

MIT licensed.

Available Tools

8 tools
logly_breakdownC

Top pages, top referrers, top countries and device/browser split for a site over the given period.

Inputs: site (required), days, from, to.

logly_eventsB

Custom event counts for a site (events sent via logly('event', ...)) over the given period.

Inputs: site (required), days, from, to.

logly_funnel_resultsC

Completion counts and drop-off per step for one conversion funnel.

Inputs: funnel_id (required), days.

logly_funnelsA

List the conversion funnels defined for a site, with their IDs and step sequences.

Inputs: site (required).

logly_install_snippetA

Return the Logly tracking snippet for a site — the single tag to add to the site's . Works offline, no API call.

Inputs: site (required).

logly_list_sitesA

List every website in the authenticated Logly account with its site ID. Start here to find the site ID the other tools need.

Inputs: no named parameters.

logly_realtimeB

Visitors currently active on a site (real-time, the last few minutes).

Inputs: site (required).

logly_statsB

Traffic totals for a site — pageviews, sessions, visitors, bounce rate, average duration — plus a daily series and a comparison against the previous period.

Inputs: site (required), days, from, to.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool maps to a distinct analytics concern: site selection, overall stats, dimensional breakdown, realtime activity, custom events, funnel definitions, funnel performance, and snippet installation. Stats and breakdown are related but their descriptions make the outputs clearly non-overlapping.

    Naming Consistency4/5

    All tools share a consistent logly_ prefix and snake_case style, which makes the set predictable. However, names mix noun-style resources like stats and events with verb-style actions like list_sites and install_snippet, so the convention is not perfectly uniform.

    Tool Count5/5

    Eight tools is a well-scoped count for a web analytics server. Each tool covers a meaningful slice of the analytics workflow without redundancy.

    Completeness5/5

    The set covers site discovery, high-level and dimensional traffic reporting, realtime monitoring, custom events, funnel definition and result retrieval, plus snippet installation. There are no obvious dead ends for the read-only analytics use case implied by the tools.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Connects Google Analytics 4 data to Claude, Cursor and other MCP clients, enabling natural language queries of website traffic, user behavior, and analytics data with access to 200+ GA4 dimensions and metrics.
      12
      2,517 PyPI
      243
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables querying Rybbit Analytics data directly through MCP-compatible clients like Claude Code. It provides tools for monitoring website statistics, user sessions, error logs, funnels, and performance metrics via natural language.
      43
      20 npm
      4
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Connects MCP clients like Claude Desktop to Google Analytics 4 Data API, enabling natural language queries for reports, top pages, traffic sources, conversions, realtime users, and period comparisons.
      7
      76 PyPI
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables querying Google Analytics 4 data using natural language through MCP clients like Claude and Cursor, supporting 200+ dimensions and metrics for traffic, user behavior, and e-commerce analysis.
      MIT