Build a Front shared-inbox 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 Front MCP server gives Claude read access to your Front workspace — conversations, contacts, accounts, inboxes, tags, teammates — 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 your support lead without losing their feedback to a screenshot circled in Preview.

Step 1 — Connect the Front MCP server

Front runs an official remote MCP server at https://mcp.frontapp.com/mcp. It authenticates over OAuth 2.1 + PKCE, so no API key is pasted into a config file — and every tool call is attributed to a specific teammate.

First, in Front, create a developer app and add an OAuth feature to it (Settings → Developers → create app), noting the Client ID and Client secret. Use https://claude.ai/api/mcp/auth_callback as the redirect URL.

In Claude Code:

Then run /mcp inside Claude Code and follow the OAuth prompt to authorize your Front workspace. When you authorize, grant the read scope only — this dashboard never needs to write to Front.

In Claude Desktop: open Settings → Connectors → Add custom connector, paste https://mcp.frontapp.com/mcp, open Advanced settings to provide your OAuth Client ID and Secret, and complete the OAuth flow the same way.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's read tools (search_conversations, list_inboxes, list_tags, list_teammates) to fetch real data:

Claude calls Front, returns the figures, and you sanity-check them against Front's own Analytics before going further. This is the moment to catch a wrong assumption — a personal inbox counted as shared, an SLA window measured in calendar hours instead of business hours, an archived conversation still counted as open — 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 first-response time the hero and put the SLA breach count under it."
• "Add a 7-day trend line for daily conversation volume."
• "Split the per-teammate table by open vs. resolved."

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 resolution time looks low, are we counting auto-replies as resolutions?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Front 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 auto-reply inbox from resolution time." 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 Front when someone opens the link. For a weekly support 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 shared-inbox dashboard needs the read scope and nothing more. Don't grant message-send or assignment scopes for a read-only reporting task.
• Check the figures before you share. The MCP returns exactly what you ask for — if your "resolution time" query counts auto-replies as the first response, or your "open" count includes a snoozed conversation, the dashboard will confidently show the wrong number. Reconcile against Front Analytics 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.