Build a Datadog reliability 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 Datadog MCP server gives Claude read access to your observability data — metrics, logs, traces and spans, monitors, hosts, incidents, dashboards — 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 an on-call team or a reliability review without losing their feedback to a screenshot circled in Preview.

Step 1 — Connect the Datadog MCP server

Datadog runs an official remote MCP server at https://mcp.datadoghq.com/api/unstable/mcp-server/mcp. You connect once; it authenticates over OAuth, so no API key is pasted into a config file.

In Claude Code:

Then run /mcp inside Claude Code and follow the OAuth prompt to authorize your Datadog organization. If you're not on the US1 site, swap the host for your region's endpoint — for example mcp.datadoghq.eu for EU.

In Claude Desktop: open Settings → Connectors → Add custom connector, paste https://mcp.datadoghq.com/api/unstable/mcp-server/mcp, and authorize with OAuth the same way.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's read tools (get_metrics, list_metrics, get_monitors, list_hosts, list_incidents, get_logs, list_spans) to fetch real data:

Claude calls Datadog, returns the figures, and you sanity-check them against your Datadog dashboards and SLO pages before going further. This is the moment to catch a wrong assumption — the wrong time window, a service tag that doesn't match, an SLO target you misremembered — 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 the error-budget burn rate the hero number and color it red under 20% remaining."
• "Add a 7-day latency trend line per service."
• "Sort the services by error rate, worst 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 checkout SLO looks too healthy, are we counting the synthetic test traffic?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Datadog 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 synthetic monitors from the error rate." 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 Datadog when someone opens the link. For a weekly reliability review or an incident postmortem snapshot, that's fine.

To make it a live canvas that always shows the current state, 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 reliability dashboard needs mcp_read and nothing more. Don't connect an account with mcp_write for a read-only reporting task.
• Check the figures before you share. The MCP returns exactly what you ask for — if your latency query spans the wrong window or your SLO target is off, the dashboard will confidently show the wrong number. Reconcile against your Datadog dashboards and SLO pages 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.