Query your Postgres database and build a 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 Postgres MCP server gives Claude read access to your database — schemas, tables, and the result of any SELECT you ask for — through a controlled set of tools. You point it at a connection string and run it in restricted (read-only) mode, so it can query but never write.
2. Claude runs the query, reads the rows, 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 Postgres MCP server

Use Postgres MCP Pro (crystaldba/postgres-mcp), a maintained server that connects to any Postgres database and runs in restricted (read-only) mode by default with --access-mode=restricted. It's a local stdio server — it runs on your machine and talks to your database directly, so nothing about your data leaves your network.

In Claude Code (via Docker — pass your connection string as DATABASE_URI):

Prefer not to use Docker? Install with pipx install postgres-mcp and point Claude at the binary instead:

In Claude Desktop: open Settings → Developer → Edit Config and add a postgres entry under mcpServers with the same command, args (--access-mode=restricted), and a DATABASE_URI env var.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the server's read tools (list_schemas, list_objects, execute_sql) to inspect your tables and run the query:

Claude inspects the schema, runs the queries, returns the figures, and you sanity-check them against a query you trust before going further. This is the moment to catch a wrong assumption — a join that double-counts, a soft-delete column you forgot to filter, a timezone in the date math — 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 weekly active users the biggest number and put new signups right under it."
• "Add a stacked bar for revenue by plan."
• "Format the currency and show signups as a 14-day sparkline."

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 active-user count looks high, are we counting internal accounts?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant 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 — exclude internal accounts from the active-user count." 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 Postgres 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 metrics dashboard needs read access and nothing more. Connect with a SELECT-only role and keep the server in --access-mode=restricted.
• Check the figures before you share. Postgres returns exactly what you ask for — if your "active users" query forgets a soft-delete filter or counts test accounts, the dashboard will confidently show the wrong number. Reconcile against a query you trust 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.