Build a GitHub PR throughput 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 GitHub MCP server gives Claude read access to your repositories — pull requests, reviews, commits, issues, contributors — 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 people without losing their feedback to a screenshot circled in Preview.

Step 1 — Connect the GitHub MCP server

GitHub runs an official remote MCP server at https://api.githubcopilot.com/mcp/. You connect once. In clients that support it, you authorize over one-click OAuth; in Claude Code today, you pass a fine-grained personal access token as a header.

First, create a fine-grained personal access token at github.com/settings/personal-access-tokens, scoped to only the repositories you want Claude to read and granted read-only repository permissions (Contents, Pull requests, Issues — Read). Then add the server:

In Claude Code:

Run /mcp inside Claude Code to confirm the server connected.

In Claude Desktop: open Settings → Connectors → Add custom connector, paste https://api.githubcopilot.com/mcp/, and authorize with one-click OAuth — granting read access only.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's read tools to fetch real data from your repo:

Claude calls GitHub, returns the figures, and you sanity-check them against the repo's own Pull requests tab and Insights before going further. This is the moment to catch a wrong assumption — the wrong default branch, bot PRs inflating the count, a fork you didn't mean to include — 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 time-to-merge the hero and put throughput right under it."
• "Add a 6-week merged-PR trend line."
• "Color the open-PR aging buckets — green under 2 days, red over a week."

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 time-to-merge looks low, are we excluding the auto-merged dependabot PRs?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant GitHub 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 bot PRs from the throughput 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 GitHub when someone opens the link. For a weekly review or a sprint retro, that's fine.

To make it a live canvas that always shows the current week'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 throughput dashboard needs read access and nothing more. Use a fine-grained token scoped to read, or a one-click OAuth grant with read access only.
• Check the figures before you share. The MCP returns exactly what you ask for — if your "merged this week" query counts bot PRs, draft PRs, or the wrong base branch, the dashboard will confidently show the wrong number. Reconcile against the repo's Pull requests tab and Insights 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.