Build a Vercel deployments 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 Vercel MCP server gives Claude read access to your Vercel account — teams, projects, deployments, build logs, and runtime logs — through a controlled set of tools. It's read-only, so it can't change or ship anything.
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 Vercel MCP server

Vercel runs an official remote MCP server at https://mcp.vercel.com. You connect once; it authenticates over OAuth, so no token is pasted into a config file.

In Claude Code:

Then run /mcp inside Claude Code and follow the OAuth prompt to authorize your Vercel account in the browser.

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

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's read tools (list_projects, list_deployments, get_deployment, get_runtime_logs) to fetch real data:

Claude calls Vercel, returns the figures, and you sanity-check them against the Vercel dashboard before going further. This is the moment to catch a wrong assumption — the wrong team, a preview deploy counted as production, a log window that's shorter than you thought — 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 deploys-this-week the biggest number and put the failure count right under it in red."
• "Add a 7-day error-rate trend line."
• "Color the recent-deployments rows red when the build failed."

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 error rate looks low, are we counting preview traffic too?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Vercel 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 preview deploys from the build-time average." 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 Vercel when someone opens the link. For a weekly deploy review or a status update, that's fine.

To make it a live canvas that always shows the latest deploys and traffic, 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 deployments dashboard needs read access and nothing more. The Vercel MCP is read-only by default — keep human confirmation on so it never deploys or buys a domain on a stray instruction.
• Check the figures before you share. The MCP returns exactly what you ask for — if your "error rate" query includes preview traffic or your build-time average counts canceled builds, the dashboard will confidently show the wrong number. Reconcile against the Vercel dashboard once.
• Don't fake the Web Vitals. Speed Insights aren't an MCP tool — if you want LCP/CLS/INP on the canvas, paste the real numbers in. A made-up vitals tile is worse than no vitals tile.
• 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.