Build a Paddle revenue 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 tile or number to leave a comment, exactly as your team would:

The three moving parts

1. The Paddle MCP server gives Claude read access to your Paddle account — subscriptions, transactions, customers, products, and reports — 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 Paddle MCP server

Paddle runs an official remote MCP server at https://mcp.paddle.com/mcp. You connect once, authenticating with a Paddle API key passed as a Bearer token — generate the key in your Paddle dashboard under Developer tools → Authentication.

In Claude Code:

Then run /mcp inside Claude Code to confirm the server connected. Paddle Billing keys are environment-bound — a sandbox key (pdl_sdbx_…) only hits sandbox, a live key only hits live — so use a live, read-scoped key for a real revenue dashboard.

In Claude Desktop: open Settings → Connectors → Add custom connector, point it at https://mcp.paddle.com/mcp, and add the same Authorization: Bearer YOUR_API_KEY header.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's tools to search the Paddle API reference and execute read calls against your account:

Claude calls Paddle, returns the figures, and you sanity-check them against the Paddle dashboard before going further. This is the moment to catch a wrong assumption — a sandbox key, a currency mix, paused subscriptions counted as active — 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:

• "Make MRR the biggest number and put churn right under it."
• "Add a 6-month MRR trend line."
• "Sort the tax breakdown by amount collected, descending."

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 tile, chart, or number they want changed and leaves a pinned comment — "this churn figure looks high, are we counting paused subscriptions as churned?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Paddle 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 number on the left looks wrong." A pinned comment on the actual tile produces "this — count paused subscriptions separately, not as churn." 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 Paddle when someone opens the link. For a weekly 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. A revenue dashboard needs read access and nothing more. Scope the Paddle API key to read-only on the resources you query.
• Check the figures before you share. The MCP returns exactly what you ask for — if your "MRR" query double-counts annual plans or treats paused subscriptions as active, the dashboard will confidently show the wrong number. Reconcile against the Paddle dashboard 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.