Build a Databricks lakehouse 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 Databricks managed MCP server gives Claude read access to your workspace — Genie spaces, Unity Catalog tables and functions, the SQL warehouse — through a controlled set of tools, governed by Unity Catalog permissions. 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 Databricks managed MCP server

Databricks ships managed MCP servers inside every workspace. The two most useful for a metrics dashboard are the Genie server (natural-language questions over your lakehouse tables) at https://<workspace-hostname>/api/2.0/mcp/genie and the SQL server at https://<workspace-hostname>/api/2.0/mcp/sql. You connect once over OAuth, and Unity Catalog permissions are always enforced — Claude only ever sees data you're allowed to see.

In Claude Code:

Then run /mcp inside Claude Code and follow the OAuth prompt to authorize the workspace. When you authorize, grant read scopes only (genie, sql) — this dashboard never needs to write to Databricks.

In Claude Desktop: open Settings → Connectors → Add custom connector, paste the same https://<workspace-hostname>/api/2.0/mcp/genie URL and your OAuth application's client ID, and authorize. (Use the custom-connector path, not the marketplace Databricks entry — Databricks requires a registered OAuth client.)

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the managed MCP server's tools to query your lakehouse through Genie and the SQL warehouse:

Claude calls Databricks, returns the figures, and you sanity-check them against the Databricks workspace before going further. This is the moment to catch a wrong assumption — the wrong catalog, a stale materialized view, a job you forgot was paused — 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 rows-processed the biggest number and put pipeline success rate right under it."
• "Add a 7-day trend line for daily rows processed."
• "Flag any gold table that hasn't refreshed in over 6 hours."

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 freshness figure looks off, is it reading the staging table instead of gold?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Databricks 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 — point it at the gold catalog, not staging." 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 Databricks 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 lakehouse dashboard needs read access and nothing more. Authorize read scopes and let Unity Catalog enforce the rest.
• Check the figures before you share. The MCP returns exactly what you ask for — if a Genie question lands on the wrong catalog or your "rows processed" query counts a backfill job, the dashboard will confidently show the wrong number. Reconcile against the Databricks workspace 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.