Build a Twilio messaging 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 Twilio MCP server gives Claude access to your Twilio account — messages, delivery status, phone numbers, usage — through a controlled set of tools generated from Twilio's own API specs. You authenticate with a scoped API key and choose which services it exposes.
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 Twilio MCP server

Twilio publishes an official MCP server as the @twilio-alpha/mcp package. It runs locally over npx and authenticates with an Account SID plus an API Key and Secret — formatted as a single SID/KEY:SECRET string — so you never paste your full Auth Token into a config file.

In Claude Code:

Replace the placeholders with a real Account SID and an API Key/Secret pair from the Twilio Console (Account → API keys & tokens → Create API key). Then run /mcp inside Claude Code to confirm the twilio server connected.

In Claude Desktop: open Settings → Developer → Edit Config, and add the server under mcpServers:

To keep the tool surface small and read-shaped, scope it to messaging with the --services or --tags flags — for example append --services twilio_api_v2010 so Claude only loads the core messaging and usage APIs.

Step 2 — Pull the numbers

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

Claude calls Twilio, returns the figures, and you sanity-check them against the Twilio Console before going further. This is the moment to catch a wrong assumption — a test-credential SID, a date range off by a timezone, a status you're counting as "delivered" that's really "sent" — 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 delivery rate the biggest number and put the failure count right under it."
• "Add a 14-day send-volume bar chart."
• "Group the failures by error code with the most common one first."

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 delivery rate looks high, are we counting queued messages as delivered?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Twilio 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 queued messages from the delivered count." 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 Twilio 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 messaging dashboard needs read access and nothing more. Use a dedicated API key and only ask Claude to fetch and summarize — never to send or configure.
• Check the figures before you share. The MCP returns exactly what you ask for — if your "delivery rate" counts queued or sent-but-not-confirmed messages as delivered, the dashboard will confidently show the wrong number. Reconcile against the Twilio Console 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.