Build a Ramp 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 Ramp MCP server gives Claude read access to your Ramp account — transactions, expenses, reimbursements, vendors, spend programs, account balances — through a controlled set of tools. It signs in as you, so it only ever sees what your own Ramp role already permits.
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 Ramp MCP server

Ramp runs an official remote MCP server at https://mcp.ramp.com/mcp. You connect once; it authenticates over OAuth — you sign in to your Ramp account through a consent screen, so no key is pasted into a config file. Your Ramp permissions come with you: the server can only read what your own role already lets you see.

In Claude Code:

Then run /mcp inside Claude Code and follow the OAuth prompt to sign in to Ramp and authorize the connection.

In Claude Desktop: open Settings → Connectors → Add custom connector, paste https://mcp.ramp.com/mcp, and authorize with OAuth the same way. There's also a one-click install from Claude's MCP directory.

Want to try it with sample data first, before pointing it at your real account? Use the demo endpoint https://demo-mcp.ramp.com/mcp instead — same flow, no Ramp account needed.

Step 2 — Pull the numbers

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

Claude calls Ramp, returns the figures, and you sanity-check them against the Ramp dashboard before going further. This is the moment to catch a wrong assumption — a date window off by a day, declined transactions counted as spend, a reimbursement state you didn't expect — 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 total spend the biggest number and put the category breakdown right under it."
• "Add a 6-month spend trend line."
• "Sort the merchants table by spend, descending, and format the currency 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 tile, chart, or number they want changed and leaves a pinned comment — "this travel category looks high, is the offsite flight batch in here?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Ramp 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 the offsite travel batch from the monthly 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 Ramp 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. Sign in with a read-scoped Ramp role, or scope a client-credentials grant to read only.
• Check the figures before you share. The MCP returns exactly what you ask for — if your "monthly spend" query includes declined or pending transactions, or straddles two billing periods, the dashboard will confidently show the wrong number. Reconcile against the Ramp 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.