How to Connect PostHog to Cursor

Query your PostHog data directly from Cursor using Sequel’s MCP server. Ask questions in plain English, with no SQL, no dashboards, and no context switching.

Short answer

Connect PostHog to Sequel, then add Sequel's MCP server to Cursor using the config on this page. Cursor can then query your live PostHog data in plain English, with no connector code and no CSV exports. Both steps take a few minutes.

Example prompts

Everything you can ask Cursor about your PostHog data.

Ask in plain English — Sequel translates it into a PostHog query, runs it, and Cursor hands back the answer. No SQL, no dashboards, no CSV exports.

What you can ask Cursor

How many unique users triggered $pageview yesterday, by country?
Show me the signup → activation funnel for users created in the last 30 days.
What's the 7-day retention of users in the 'Power users' cohort?
Which 10 feature flags have the most evaluations this week?
Compare conversion rate by browser for the checkout funnel.

How it works

Three steps to get started

Connect PostHog to Sequel

In your Sequel dashboard, go to Connections and add PostHog. Sequel handles authentication and schema discovery automatically.

Add Sequel to the agent

Copy the Sequel MCP configuration into Cursor's settings file (shown below). Swap in your API key from Settings → API Keys.

Ask Cursor about your data

Restart Cursor and start asking questions. "How many unique users triggered $pageview yesterday, by country?" — and get a real answer backed by live PostHog data.

Why Cursor

What Cursor does with your PostHog data

Schema exploration in your editor

Ask Cursor to describe your database schema, find the right table for a feature, or understand relationships between tables — all without switching to another tool or reading through migrations.

Query data while you code

Need to check actual data while implementing a feature? Ask Cursor to pull examples from your connected databases. No more copy-pasting connection strings into a separate SQL client.

Catch data issues before they ship

Run queries against your staging or production database from inside the editor. Validate assumptions about data shape, volume, or edge cases while the code is still in front of you.

Configuration

Add Sequel to Cursor

Place this in .cursor/mcp.json and replace sql_your_api_key with a key from Settings → API Keys.

.cursor/mcp.json

{
  "mcpServers": {
    "sequel": {
      "url": "https://api.sequel.sh/mcp",
      "headers": {
        "Authorization": "Bearer sql_your_api_key"
      }
    }
  }
}

Install

Install PostHog MCP in Cursor

Pick your app and Sequel installs itself: a one-click link where the client supports it, that client’s own few steps where it doesn’t. Every route signs in with your Sequel account over OAuth, so there is no API key to copy and nothing to keep in sync.

Already have an MCP client?

https://api.sequel.sh/mcp

Add it as a remote (streamable HTTP) server and sign in when prompted. Skills come with it; nothing else to install. Manual setup per client

Add Sequel to Cursor

One click: the button above opens Cursor with Sequel pre-filled, and Cursor signs you in with your Sequel account. There is no key to paste.

Other AI agents

Connect PostHog MCP to any agent

Claude

Use Claude to query your databases, explore schemas, and build analyses — all from one conversation.

Cursor

Query your databases and explore schemas without leaving your code editor.

ChatGPT

Connect ChatGPT to your databases and get data-backed answers in every conversation.

VS Code

Get database access inside VS Code Copilot without leaving your editor.

Windsurf

Give Windsurf's Cascade AI access to your databases — query data without leaving your editor.

Zed

Connect Zed's AI assistant to your databases for real-time data access while you code.

Gemini

Connect Google Gemini to your databases for grounded, data-backed answers.

Claude Code

Query your databases directly from the Claude Code CLI — without leaving your terminal.

Codex

Give OpenAI Codex CLI real-time database access for data-grounded coding sessions.

OpenClaw

Turn your self-hosted OpenClaw agent into a data analyst that queries every source you've connected.

Hermes

Give Nous Research's Hermes agent read access to every database and marketing tool you've connected.

Grok Bot

Tell your Grok bot to add Sequel and it can query every database and marketing tool you've connected.

Muse

Give Meta's Muse one message and it builds its own connector to every source you've put in Sequel.

dots

Add Sequel once in ChatGPT and your dot can answer data questions on its own, day and night.

Other data sources

Connect other sources to Cursor

PostgreSQL

Query your PostgreSQL database in plain English. No SQL required.

MySQL

Instant insights from your MySQL database. Ask in plain English.

ClickHouse

Real-time analytics on ClickHouse at any scale, in plain English.

BigQuery

Query petabytes of BigQuery data in plain English.

Google Sheets

Query, write, and manage Google Sheets with AI.

Google Analytics 4

Ask your GA4 data anything. No SQL, no dashboards.

Google Search Console

Unlock your SEO data with natural language. No exports, no pivot tables.

MCP Server

Connect any MCP-compatible server and query it with AI in seconds.

Stripe

Ask your Stripe data anything. MRR, churn, refunds — answered in plain English.

Polar

Ask your Polar revenue, subscriptions, and usage data anything — in plain English.

Dodo Payments

Ask questions about payments, subscriptions, refunds and payouts in plain English.

Mixpanel

Conversational analytics on your Mixpanel events, funnels, and retention.

Amplitude

Query your Amplitude taxonomy, funnels, and dashboards in plain English.

HubSpot

Your AI analyst for HubSpot contacts, deals, tickets, and pipelines.

Ahrefs

Ask your Ahrefs SEO data anything: backlinks, keywords, and traffic.

Apollo.io

Ask your Apollo.io prospects, contacts, and accounts anything, in plain English.

Cloudflare D1

Ask your Cloudflare D1 database questions in plain English.

Instagram

Instagram organic analytics — post engagement, reach, and audience insights in plain English.

Frequently asked questions

How do I connect PostHog to Cursor?

You need two things: (1) connect PostHog to Sequel in your Sequel dashboard under Connections, and (2) add the Sequel MCP config to Cursor using the setup shown above. Once both are done, Cursor can query your PostHog data directly.

What PostHog data can Cursor access?

Cursor can access any data available through your PostHog connection in Sequel. Use Sequel's search tool to discover available metrics and dimensions, then execute queries to pull the data you need.

Is my PostHog data sent to Cursor's servers?

Query results are returned to Cursor as context within your conversation. Only the data you explicitly ask about is retrieved. Sequel never stores your query results permanently — they exist only for the duration of the tool call.

Do I need a Sequel account?

Yes. You need a Sequel account to connect PostHog and generate an API key. Sign up free at sequel.sh — no credit card required. Then create a connection to PostHog and generate an API key from Settings → API Keys.

Can I connect multiple PostHog accounts?

Yes. Sequel supports multiple connections of the same type. If you have multiple PostHog accounts or properties, add each as a separate connection in Sequel. Cursor will be able to query all of them.

Does this work with Cursor Agent and Cursor Chat?

Yes. Once the MCP config is in your .cursor/mcp.json, Sequel tools are available in both Cursor Chat and Cursor Agent. The agent can call multiple tools in sequence to answer complex questions.

Should I use a project-level or global MCP config?

Use a project-level .cursor/mcp.json for team repos so all collaborators share the same MCP setup. For personal access, add the config globally at ~/.cursor/mcp.json instead.

Can Cursor modify my database through Sequel?

Sequel's query tools are read-only by default. The workbench tool can run Python code, which could write to files, but it runs in an isolated sandbox without direct database write access.

How do I share the Sequel MCP config with my team?

Commit .cursor/mcp.json to your repo. Each team member needs their own Sequel API key — replace the value of the Authorization header with their personal key from Settings → API Keys.

How do I connect PostHog to Sequel?

Create a Personal API Key in PostHog under Settings → Personal API Keys with read-only scopes: query:read, event_definitions:read, property_definitions:read, insight:read, cohort:read, project:read. Paste it into Sequel along with your host (US Cloud, EU Cloud, or self-hosted base URL) and your numeric project ID, then click Test.

Does Sequel work with PostHog Cloud and self-hosted PostHog?

Both. For PostHog Cloud, use https://us.posthog.com or https://eu.posthog.com. For self-hosted, point the host field at your own base URL (no trailing slash) — as long as the same Personal API Key endpoints exist, Sequel works identically.

What is HogQL, and why does it matter?

HogQL is PostHog's SQL dialect that runs against the raw events table. It's strictly more expressive than the insight builder — joins, window functions, conditional aggregations. Sequel writes HogQL under the hood, which is why it can answer questions a built-in insight can't.

Can Sequel write or change anything in PostHog?

No. The connector only ships read-only tools (HogQL query, list events, list properties, list insights, list cohorts) and works with read-only scopes. The agent cannot create insights, dashboards, cohorts, or feature flags.

Connect PostHog to Cursor today

Get started free View all integrations