Home Tutorials Categories Skills About
ZH EN JA KO
🦔

PostHog

Product Analytics Search & Productivity

Install Command

npx clawhub@latest install posthog

Installation Guide

1
Check Environment

Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.

2
Run Installation

Run the install command above in your terminal. ClawHub will automatically download and install PostHog to the ~/.openclaw/skills/ directory.

3
Verify Installation

Run openclaw skills list to check your installed skills and confirm PostHog appears in the list.

4
Configure (Optional)

Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.

Manual Installation: Copy the Skill folder to ~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
Query event and user behavior data Create and analyze conversion funnels Manage feature flags and A/B tests

Detailed Description

PostHog MCP Server integrates the open-source product analytics platform into AI, enabling you to query user behavior data, analyze conversion funnels, and manage feature flags using natural language.

Core Features

  • Event Querying: Query user behavior event data with filtering by properties, time range, and aggregate statistics
  • Funnel Analysis: Create multi-step conversion funnels to identify user drop-off points and conversion rate bottlenecks
  • Feature Flags: View and manage feature flags, understand A/B test results

Configuration

{
  "mcpServers": {
    "posthog": {
      "command": "npx",
      "args": ["-y", "mcp-posthog"],
      "env": {
        "POSTHOG_HOST": "https://app.posthog.com",
        "POSTHOG_API_KEY": "Your personal API key",
        "POSTHOG_PROJECT_ID": "Project ID"
      }
    }
  }
}

Use Cases

  • Query key product metrics in natural language, such as DAU and retention rate
  • Analyze registration-to-payment conversion funnels to pinpoint drop-off stages
  • Check feature flag activation status and user coverage percentage
  • Compare behavioral differences across user cohorts