Think inside your AI world.
How do I connect PostHog to ChatGPT?
PostHog's free hosted server answers ChatGPT with the same eighty-tool surface it gives every client — and the measured lane is live: if it speaks MCP, Unl can reach it.
Direct answer: connect PostHog's free hosted MCP server to ChatGPT. In ChatGPT, add it from the connector settings (developer mode); the tool's own docs carry the current path. Authorised, ChatGPT reads trends and funnels; retention; HogQL queries and insights; dashboards and feature flags; experiments with their results; error tracking, cohorts, session data and the LLM cost ledger. Separately: through Unl the measured read is present-tense for this tool, whatever surface you ask from, and the lane is open to any tool that speaks MCP.
Eighty tools, any client
The funnel, the flag states, the experiment arms, the HogQL cut — conversationally available in ChatGPT exactly as elsewhere. Access to analytics is a solved problem; this server is the proof.
Definitions freeze during experiments
Worked case: you ratified a metric-freeze rule — no dashboard definition changes while an experiment is running, because a mid-test tweak to the activation insight once made the arms incomparable and burned three weeks. PostHog versions insights; that changes wait for the test to end is experimental hygiene you imposed.
Through Unl the dashboard read arrives with the freeze active: an insight edit is pending while the pricing test runs — held by your rule, the incomparable-arms story attached. The lane is live for PostHog today, so this is not a pattern description; it is the shipped behaviour.
PostHog to ChatGPT is the same free hosted server in a different client; through Unl it is live now — the analytics read arriving inside your experimental discipline, on every surface you work from.
Reads through Unl arrive with measured context — in the presence of the decisions you’ve already settled. The reach lane is live: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Read further
Questions people ask
What does PostHog's server give ChatGPT?
The same ~80 tools it gives everyone: trends, funnels, retention, HogQL, insights, dashboards, flags, experiments with results, error tracking, cohorts, session data, LLM cost.
What is different about PostHog and Unl?
Measured reads of your PostHog data are shipped behaviour today through Unl's live reach lane, and the lane is open: one box, paste anything, and if it speaks MCP, Unl can reach it.
Does the freeze rule block edits mechanically?
No — Unl reads and measures; it never mutates your PostHog project. The rule arrives inside the conversation where the edit is proposed, which is where freezes actually hold or break.
What this is
Think inside your AI world — you stay in command
Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.
It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.
Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:
Alpha is invite-only · free at launch.