Build a CircleCI build-health 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 CircleCI MCP server gives Claude read access to your CircleCI org — pipeline status, job test results, build failure logs, flaky tests, usage metrics — through a controlled set of tools. You authorize it with a personal API token.
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 CircleCI MCP server

CircleCI ships an official MCP server you run locally over npx. It authenticates with a personal API token, which you create once in your CircleCI account.

First, create a read-scoped personal API token at app.circleci.com/settings/user/tokens.

In Claude Code:

Replace your-circleci-token with the token you just created, then run /mcp inside Claude Code to confirm the server connected.

In Claude Desktop: open Settings → Developer → Edit Config, and add circleci-mcp-server with command npx, args ["-y", "@circleci/mcp-server-circleci@latest"], and CIRCLECI_TOKEN in env.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's read tools (get_latest_pipeline_status, get_job_test_results, find_flaky_tests, download_usage_api_data, list_followed_projects) to fetch real data:

Claude calls CircleCI, returns the figures, and you sanity-check them against the CircleCI dashboard before going further. This is the moment to catch a wrong assumption — the wrong branch, a project you don't own, a status filter that excludes canceled runs — 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 success rate the biggest number and put average duration right under it."
• "Color the recent-runs table by status — green for success, red for failed."
• "Add a 6-week build-duration trend line."

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 duration looks low, is it excluding the queued time?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant CircleCI 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 — measure wall-clock duration including queue time, not just execution." 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 CircleCI when someone opens the link. For a weekly build-health review or a sprint retro snapshot, that's fine.

To make it a live canvas that always shows the latest builds, 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 build-health dashboard needs read access and nothing more. The MCP server can rerun and roll back pipelines — don't ask it to for a reporting task, and scope your token to a user who can't trigger production deploys if you want a hard guarantee.
• Check the figures before you share. The MCP returns exactly what you ask for — if your "success rate" query counts canceled runs as failures, or your "duration" excludes queue time, the dashboard will confidently show the wrong number. Reconcile against the CircleCI 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.