Build a Google Ads 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 Google Ads MCP server gives Claude read access to your Google Ads account — campaigns, ad groups, keywords, spend, and conversion metrics — through a controlled set of tools. The official server is read-only by design.
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 Google Ads MCP server

Google publishes an official Google Ads MCP server. It runs locally with pipx and reads your account through the Google Ads API. You'll need a developer token (Explorer access is enough), a Google Cloud project ID, and OAuth credentials — set up Application Default Credentials once and the server uses them.

Authorize the read scope once with the gcloud CLI:

In Claude Code, register the server (swap in your token and project ID):

In Claude Desktop: open Settings → Connectors → Add custom connector and add the same pipx run --spec git+https://github.com/googleads/google-ads-mcp.git google-ads-mcp command, with GOOGLE_PROJECT_ID and GOOGLE_ADS_DEVELOPER_TOKEN set in the connector's environment.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's read tools (list_accessible_customers, then search with a GAQL query) to fetch real data:

Claude calls Google Ads, returns the figures, and you sanity-check them against the Google Ads UI before going further. This is the moment to catch a wrong assumption — the wrong customer ID, a conversion action you didn't mean to count, a date range off by a day — 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 ROAS the biggest number and put spend right under it."
• "Add a 7-day spend-vs-conversions trend line."
• "Highlight any campaign with ROAS under 2.0 in red."

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 campaign row they want changed and leaves a pinned comment — "this ROAS looks high, are we counting view-through conversions?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant GAQL 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 view-through conversions from ROAS." 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 Google Ads 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 performance dashboard needs read access and nothing more. The official Google Ads MCP server is read-only, and the adwords scope is all you should authorize.
• Check the figures before you share. The MCP returns exactly what your GAQL query asks for — if your ROAS divides by the wrong cost or your conversions include an action you didn't mean to count, the dashboard will confidently show the wrong number. Reconcile against the Google Ads UI 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.