Connect PostHog to your AI chat agent
Product analytics questions rarely fit a fixed report menu. HogQL, PostHog's own query language, lets your agent ask whatever you'd actually ask.
SourcetoMCP connects it straight to Claude, ChatGPT, or any MCP-compatible agent, so it can query real events and people, check feature flags, and turn one on or off. It sits on the same connection as your ad accounts, Search Console and Google Analytics, so one question can cross all of them: what a campaign cost, what it sent you, and what those people then did in the product.
Agent asks
What's our week-over-week signup trend?
Agent asks
Turn off the new-checkout-flow flag for everyone.
Why PostHog data matters for your agent
Product questions don't come pre-shaped into the handful of report types most analytics tools offer. Your agent should be able to ask the question you actually have, in the shape you have it.
- A real query language. HogQL covers trends, funnels, breakdowns, and retention-shaped questions in one general capability, so you are never stuck with the closest item on a fixed menu.
- People, as well as aggregate numbers. Ask about a specific user by name, email, or distinct id and get their real profile back, with every property and merged device id on it.
- Feature flags your agent can actually see and use. Check what's live, and turn something off the moment it looks wrong, in the same conversation where you noticed it.
- Deliberately narrow write access. The only thing your agent can change is a flag's on/off switch. Who it targets and its rollout percentage stay put.
How it works
Connect PostHog. Paste a Personal API Key from your PostHog account settings, pick US Cloud, EU Cloud, or your self-hosted URL, and choose which project your agent can access.
Your agent asks in plain language. It writes the HogQL query, or calls the right lookup, behind the scenes and gets real data back.
Every answer shows its work. Structured rows come back keyed by the query's own columns, so you can see exactly what was asked instead of taking the summary on faith.
Event counts
SELECT event, count() FROM events ... GROUP BY event
| event | count() |
|---|---|
| $pageview | 48,204 |
| signed_up | 1,382 |
| checkout_completed | 969 |
Ask about your PostHog data. Get real answers back.
‖ manual mode on
Built for whatever you actually want to ask
Query your data with real HogQL
Your agent writes a SELECT against your events, persons, and sessions, so trends, funnels, breakdowns, and retention-shaped questions all come from the same operation.
Look up any person
Search by name, email, or distinct id and get back their full profile: every property, every merged device id, first and last seen.
See every feature flag's real state
Key, name, active or archived, and the raw release-condition configuration, including rollout percentage and targeted groups, exactly as PostHog stores it.
Turn a flag on or off from the conversation
Ask your agent to disable a flag and it does, immediately, then reads back the real post-change state rather than assuming the request worked.
Safety by default on the one write action
Toggling a flag only ever changes whether it is on. Its targeting, rollout percentage, and audience stay exactly as they were, and you say active or inactive rather than relying on a default.
Connects with your own API key
Paste a personal API key scoped to exactly what you want to grant. There is no app to approve and no consent screen, and you can revoke the key from PostHog whenever you want.
Works with Cloud or self-hosted
US Cloud, EU Cloud, or your own self-hosted instance's URL, the same connector either way.
Answers that match your real project
Every query runs against your actual project. If an event or property doesn't exist, your agent finds that out from PostHog itself.
Real prompts teams run against PostHog
Every SourcetoMCP account gets these in the Prompt Library, ready to run against your own connected PostHog project.
Feature flag management
- PostHog Feature Flag Regression Kill Switch
- PostHog Stale Feature Flag Audit
Ask anything else
Your agent can call these operations directly too, querying events, people, and flags in your own words. The library is a starting point.
PostHog MCP FAQ
Common questions from teams connecting PostHog to an agent.
Anything expressible as a HogQL query against your events, persons, and sessions, plus dedicated lookups for people and feature flags, and the ability to turn a feature flag on or off: 4 registered operations in total.
Claude, ChatGPT, Cursor, or any MCP-compatible client. Connect once from your dashboard's "Connect an agent" page and every tool you've paired can use it.
No. PostHog doesn't use an OAuth app for this the way most of our other connectors do. You paste a Personal API Key from your own PostHog account settings, scoped to whatever projects that key can already see, and revoke it from PostHog any time.
In one narrow way: it can turn an existing feature flag on or off. It can't create new flags, and it can't change who a flag targets (release conditions, rollout percentage). Nothing else in PostHog is written to.
Real data. HogQL queries run directly against your project's own events, persons, and sessions tables, the same data PostHog's own product uses.
Yes. When connecting, choose US Cloud, EU Cloud, or enter your own self-hosted instance's URL.
PostHog is available on paid plans. See Pricing for how many connections each plan includes.
