Build a Brex spend 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 Brex MCP server gives Claude read access to your Brex account — card spend, expenses, budgets and spend limits, banking transactions, vendors — 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 finance and budget owners without losing their feedback to a screenshot circled in Preview.

Step 1 — Connect the Brex MCP server

Brex runs an official remote MCP server at https://api.brex.com/mcp. First, an account or card admin enables it once in the Brex dashboard: Settings → Early access → turn on "Brex in AI assistants", and accept the Developer API agreement under Settings → Developer. Then you connect from Claude; it authenticates over OAuth, so no key is pasted into a config file.

In Claude Code:

Then run /mcp inside Claude Code and follow the OAuth prompt to authorize your Brex account. The MCP server requests exactly the scopes its tools need and you approve them on the consent screen — grant read access only, since this dashboard never writes to Brex.

In Claude Desktop: open Settings → Connectors → Add custom connector, paste https://api.brex.com/mcp, and authorize with OAuth the same way.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the Brex MCP server's read tools to fetch real data:

Claude calls Brex, returns the figures, and you sanity-check them against the Brex dashboard before going further. This is the moment to catch a wrong assumption — a partial billing period, pending versus settled transactions, a budget that resets mid-month — 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:

• "Flag any budget over 80% used in red."
• "Add spend-by-department as a horizontal bar chart."
• "Format the currency and round to whole dollars."

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 budget bar, department, or number they want changed and leaves a pinned comment — "this engineering budget looks over, are we counting pending transactions?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Brex 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 pending transactions from the budget 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 Brex when someone opens the link. For a weekly spend 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 spend dashboard needs read access and nothing more. Scope the OAuth grant or API token accordingly.
• Check the figures before you share. The MCP returns exactly what you ask for — if your "spend this month" query includes pending authorizations or a budget that already reset, the dashboard will confidently show the wrong number. Reconcile against the Brex 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.