Build a PostHog funnel & activation dashboard with Claude

This is an end-to-end example: connect a data source over MCP, generate a dashboard from live numbers, and close the review loop on one link. Total time, start to shared link, is under fifteen minutes. The same shape works for any of the other examples — only the connection step changes.

Here's the finished dashboard, published to a canvas — click any funnel step or tile to leave a comment, exactly as your team would:

The three moving parts

1. The PostHog MCP server gives Claude read access to your product analytics — funnels, trends, retention, saved insights, and raw HogQL/SQL queries — through a controlled set of tools. You approve what it can touch.
2. Claude pulls the numbers and writes a single self-contained HTML dashboard. You iterate on it in the artifact panel until it's right.
3. Drafty turns that HTML into a stable link your team reviews. Comments pin to the exact element; Claude ships the fix to the same URL.

The generation step is fast now. The part this example is really about is the third one — getting the dashboard in front of people without losing their feedback to a screenshot circled in Preview.

Step 1 — Connect the PostHog MCP server

PostHog runs an official remote MCP server at https://mcp.posthog.com/mcp. You connect once; the first call sends you through a browser login that authorizes the account and routes you to the right data region (US or EU) automatically — no key pasted into a config file.

In Claude Code:

Then run /mcp inside Claude Code and follow the login prompt to authorize the account. When you authorize, grant read access only — this dashboard never needs to write to PostHog.

In Claude Desktop: open Settings → Connectors → Add custom connector, paste https://mcp.posthog.com/mcp, and authorize through the browser login the same way.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's read tools (query-funnel, query-trends, query-retention, execute-sql, insights-list) to fetch real data:

Claude calls PostHog, returns the figures, and you sanity-check them against your PostHog insights before going further. This is the moment to catch a wrong assumption — the wrong "activated" event, a date range off by a week, internal test users not filtered out — while it's cheap.

Step 3 — Build the dashboard

Once the numbers look right, ask for the artifact:

Claude renders it live in the artifact panel. Iterate in place — you're not regenerating from scratch:

• "Show the drop-off percentage between each funnel step, not just the count."
• "Add a sparkline for the 8-week WAU trend."
• "Sort the first-week events by share of users, highest first."

Step 4 — Publish to Drafty for review

A Claude artifact link is a preview, not a stable URL — iterate the artifact and the link you already sent now shows the old version. Ask Claude to publish it to a Drafty canvas instead, so the link you share always stays current:

Claude pushes the dashboard and hands back a drafty.im/canvas/… link that renders on any device. Send it — your team opens it in a browser, no login and no Claude account needed.

Step 5 — The review loop

This is the part that's not obvious until you've done it once.

A reviewer clicks the specific funnel step, tile, or number they want changed and leaves a pinned comment — "this onboarding step looks too lossy, are we counting people who skipped it?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant PostHog query if needed, and pushes a revised dashboard to the same URL. The reviewer refreshes and sees the change; the thread stays attached to the element.

The mechanic matters because of what it removes. A Slack message about a chart produces "the funnel on the left looks wrong." A pinned comment on the actual step produces "this — the drop here is double-counting users who came back later." One of those produces a correct revision; the other produces a guess.

Keeping it fresh

An MCP-generated dashboard is a snapshot — it holds the numbers Claude pulled when it built it; it doesn't re-query PostHog when someone opens the link. For a weekly product review or a board-ready snapshot, that's fine.

To make it a live canvas that always shows today's figures, copy this prompt — Claude sets up the refresh for you and schedules it to run on its own:

The link stays stable while the content updates underneath it — see keeping a canvas updated automatically.

What to watch for

• Read-only, always. An activation dashboard needs read access and nothing more. Scope the authorization or personal API key accordingly.
• Check the figures before you share. The MCP returns exactly what you ask for — if your funnel uses the wrong "activated" event or your date window is off, the dashboard will confidently show the wrong conversion. Reconcile against your PostHog insights once.
• The link is the deliverable, not the artifact. Share the Drafty URL, not the Claude artifact preview — that's the one you can update in place.