Lovable integration

The PostHog MCP lets Lovable query your analytics data, investigate errors, manage feature flags, and run experiments - all through natural language.

Connect PostHog to Lovable

Custom MCP servers require a paid Lovable plan.

Go to Settings → Connectors → Personal connectors
Click New MCP server
Enter the name PostHog and URL https://mcp.posthog.com/mcp
Under Authentication, select OAuth
Click Add & authorize, then log in to PostHog when prompted

The PostHog MCP server is now available in your Lovable chats.

Set up PostHog in your project

Once connected, give Lovable this prompt to add PostHog to your app:

text
Install posthog-js.

Get credentials via MCP: Use the PostHog MCP projects-get tool to discover the project token and host. Do NOT hardcode placeholder keys.

Initialize at module top-level in the main App file (NOT inside useEffect):

import posthog from 'posthog-js'
import { PostHogProvider } from 'posthog-js/react'

posthog.init(POSTHOG_TOKEN, {
  api_host: HOST,
  person_profiles: 'identified_only',
  capture_pageview: false,
  capture_pageleave: true,
  autocapture: true,
})

function App() {
  return <PostHogProvider client={posthog}>...</PostHogProvider>
}

capture_pageview must be false — PostHogProvider automatically tracks page views on route changes. Setting it to true would only capture the initial load and miss all SPA navigations.

Error tracking: Enable Exception Autocapture in PostHog project settings (Settings → Error Tracking). The SDK handles uncaught errors automatically — do NOT add manual window.onerror or onunhandledrejection handlers (they'd create duplicates).

Custom events: Use posthog.capture() for domain-specific events (e.g., game_started, stage_transition, button_clicked).

The agent will get your project credentials from the MCP, install posthog-js, and set up analytics with automatic pageview tracking, error capture, and autocapture.

What you can do with the MCP

Once connected, you can ask Lovable to interact with your PostHog data directly:

Query your analytics

Prompt: "How many unique users signed up in the last 7 days, broken down by day?"

The agent will run a trends query and return daily signup counts with a breakdown.

Prompt: "What's the conversion rate from signup to first purchase?"

The agent will build a funnel query and calculate the conversion percentage between those two events.

Investigate errors

Prompt: "What are the top 5 errors in my project this week?"

The agent will fetch error groups sorted by occurrence count, including how many users were affected.

Prompt: "Show me details about the most recent TypeError"

The agent will pull the stack trace, affected users, and browser/OS context for that error.

Manage feature flags

Prompt: "Create a feature flag called 'new-checkout' enabled for 10% of users"

The agent will create the flag with a 10% rollout and return the configuration with a link to the flag in PostHog.

Prompt: "Update the 'beta-features' flag to 50% rollout"

The agent will modify the existing flag and confirm the new rollout percentage.

Run experiments

Prompt: "Create an A/B test for the pricing page that measures conversion to checkout"

The agent will set up an experiment with control/test variants and configure a funnel metric measuring pricing page to checkout conversion.

See all available MCP tools for the complete list.

Troubleshooting

OAuth not refreshing

If the OAuth token expires and won't refresh, you can use a personal API key instead:

Create a personal API key with the MCP Server preset
In Lovable, edit the PostHog MCP connection
Change authentication to Bearer and enter your API key

MCP not connecting

Try disconnecting and reconnecting the PostHog MCP server. Make sure you're logged into the correct PostHog account.