Build a Snowflake warehouse 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 Snowflake-managed MCP server gives Claude governed access to your account — warehouse metering, query history, storage, and the rest — through a controlled set of tools, all under the RBAC of the role you grant. 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 Snowflake-managed MCP server

Snowflake runs a managed remote MCP server scoped to your account. You create the server and an OAuth security integration once in Snowflake, then point Claude at the server's URL — which looks like https://<account>.snowflakecomputing.com/api/v2/databases/<db>/schemas/<schema>/mcp-servers/<name>. Auth is OAuth, so no password or key lands in a config file.

In Claude Code:

Then run /mcp inside Claude Code and follow the OAuth prompt to authorize against your account. Authorize with a role that has read access to the usage views — this dashboard never needs to write.

In Claude Desktop: open Settings → Connectors → Add custom connector, paste the same MCP server URL, enter the client ID and secret from your OAuth security integration, and authorize through the Snowflake login that opens.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's SQL and analyst tools to query your usage views and return real data:

Claude runs the queries, returns the figures, and you sanity-check them against the Snowsight usage and warehouse-activity pages before going further. This is the moment to catch a wrong assumption — a warehouse you forgot was running, credits attributed to the wrong cost center, a latency average skewed by one runaway query — 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:

• "Sort the warehouse bars by credits, descending."
• "Add a 6-month credit-consumption trend line."
• "Flag any warehouse over its monthly budget in red."

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 credit total looks low, are we including serverless tasks?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Snowflake 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 — include serverless and Snowpipe credits in the warehouse total." 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 Snowflake when someone opens the link. For a weekly cost 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 warehouse dashboard needs read access to the usage views and nothing more. Scope the role you authorize accordingly.
• Check the figures before you share. The MCP returns exactly what you ask for — if your credit query omits serverless or Snowpipe usage, or ACCOUNT_USAGE latency (which can lag a couple of hours) is treated as real-time, the dashboard will confidently show the wrong number. Reconcile against Snowsight 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.