Do I need to paste a Mixpanel secret anywhere?

No. The remote Mixpanel MCP server at mcp.mixpanel.com authenticates over OAuth, so you authorize through a consent screen instead of pasting a key — and you only ever reach projects you already have permission to view. For an unattended agent, use a read-scoped Mixpanel Service Account, never committed to a repo.

Is the dashboard live or a snapshot?

A snapshot. It contains the numbers Claude pulled when it built the file; it does not re-query Mixpanel when someone opens the link. To refresh it, ask Claude to repull and re-push to the same URL — or put that on a daily schedule so the stable link always shows current numbers.

Can my team comment without a Mixpanel or Claude account?

Yes. The dashboard is published to a Drafty canvas link that renders in any browser. Reviewers click the exact element they want changed and leave a pinned comment with no login required. Only the person connecting Mixpanel needs access to the project.

Is it safe to give Claude access to my Mixpanel project?

Connect with OAuth or a read-scoped service account, and a product dashboard never needs more than that. Every tool call is mediated by the MCP server, you can only reach projects you already have permission to view, and in Claude you approve actions. Don't grant write or admin access for a read-only reporting task.

How is this different from a Mixpanel board or saved report?

Mixpanel boards and saved reports query live data against the models you maintain in Mixpanel — the right choice for governed, recurring product analytics. This approach is for a fast, shareable snapshot you can spin up in minutes and iterate by talking to Claude, then collect feedback on inline. Different jobs: one is a standing system, the other is a quick reviewable deliverable.

drafty

Build a Mixpanel product dashboard with Claude

Connect the Mixpanel MCP server to Claude, ask for an events and retention dashboard from your live product data, and publish it to a link your team comments on directly — no BI tool, no screenshots pasted into Slack.

What you'll build

A self-contained product dashboard — daily active users, top events, a signup-to-activation funnel, and a weekly retention curve — generated by Claude from your real Mixpanel data, then published to a drafty.im/canvas/… link. Your team clicks the exact chart or number they want changed and leaves a note. Claude reads the comments and ships a revised version to the same URL.

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:

Live canvas — comment on any elementOpen ↗

The three moving parts

The Mixpanel MCP server gives Claude read access to your Mixpanel project — events, funnels, flows, retention, cohorts, saved reports — through a controlled set of tools. You only ever see projects you already have permission to view.
Claude pulls the numbers and writes a single self-contained HTML dashboard. You iterate on it in the artifact panel until it's right.
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 Mixpanel MCP server

Mixpanel runs an official remote MCP server at https://mcp.mixpanel.com/mcp. You connect once; it authenticates over OAuth, so no key is pasted into a config file.

In Claude Code:

claude

❯

claude mcp add --transport http mixpanel https://mcp.mixpanel.com/mcp▌

Then run /mcp inside Claude Code and follow the OAuth prompt to authorize your Mixpanel account. (On the EU or India residency, use https://mcp-eu.mixpanel.com/mcp or https://mcp-in.mixpanel.com/mcp instead.)

In Claude Desktop or claude.ai: go to Settings → Connectors (or claude.ai/customize/connectors), add Mixpanel, and complete the same OAuth flow in your browser.

Safety first

Connect over OAuth — you authorize through Mixpanel's consent screen instead of pasting a credential, and you only ever reach projects you can already see. For an unattended agent, Mixpanel offers a read-scoped Service Account for static credentials; never paste it into a committed config file. The dashboard only reads; it has no reason to hold write or admin permissions.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the Mixpanel MCP server's read tools to query your project's events, funnels, and retention:

claude

❯

Using the Mixpanel MCP server, pull everything we need for a product dashboard: daily active users for the last 30 days, the 8 most-fired events this week with counts, a signup → first key action → activation funnel with conversion at each step, and a weekly retention curve for users who signed up in the last 8 weeks. Summarize the figures before you build anything.▌

Claude calls Mixpanel, returns the figures, and you sanity-check them against the Mixpanel reports before going further. This is the moment to catch a wrong assumption — the wrong project, a date range off by a day, an event name that doesn't mean what you think — while it's cheap.

Step 3 — Build the dashboard

Once the numbers look right, ask for the artifact:

claude

❯

Build a single self-contained HTML dashboard from those figures. Daily active users as the hero number with a 30-day trend line, then a top-events list, an activation funnel showing conversion at each step, and a weekly retention curve. Clean, no external dependencies — inline the CSS and any chart code.▌

Claude renders it live in the artifact panel. Iterate in place — you're not regenerating from scratch:

"Make DAU the biggest number and show week-over-week change under it."
"Turn the retention numbers into an actual curve, not a table."
"Drop trial accounts from the activation funnel."

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

❯

Publish this dashboard to Drafty as a canvas and give me the shareable link.▌

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 retention curve looks flat, are we counting users who never activated?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Mixpanel 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 funnel on the left looks wrong." A pinned comment on the actual tile produces "this — split the activation step by platform." 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 Mixpanel 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:

claude

❯

Turn this Mixpanel dashboard into a live canvas: every morning, re-pull the latest DAU, events, funnel, and retention numbers from Mixpanel via the MCP server, rebuild the dashboard, and push a new version to the same canvas URL so the link always shows today's figures. Schedule it to run daily 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 product dashboard needs read access and nothing more. Connect with OAuth or a read-scoped service account.
Check the figures before you share. The MCP returns exactly what you ask for — if your retention window is off, or your funnel includes test events, the dashboard will confidently show the wrong number. Reconcile against the Mixpanel reports 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.

Mixpanel dashboard with Claude — FAQ

Do I need to paste a Mixpanel secret anywhere?: No. The remote Mixpanel MCP server at mcp.mixpanel.com authenticates over OAuth, so you authorize through a consent screen instead of pasting a key — and you only ever reach projects you already have permission to view. For an unattended agent, use a read-scoped Mixpanel Service Account, never committed to a repo.
Is the dashboard live or a snapshot?: A snapshot. It contains the numbers Claude pulled when it built the file; it does not re-query Mixpanel when someone opens the link. To refresh it, ask Claude to repull and re-push to the same URL — or put that on a daily schedule so the stable link always shows current numbers.
Can my team comment without a Mixpanel or Claude account?: Yes. The dashboard is published to a Drafty canvas link that renders in any browser. Reviewers click the exact element they want changed and leave a pinned comment with no login required. Only the person connecting Mixpanel needs access to the project.
Is it safe to give Claude access to my Mixpanel project?: Connect with OAuth or a read-scoped service account, and a product dashboard never needs more than that. Every tool call is mediated by the MCP server, you can only reach projects you already have permission to view, and in Claude you approve actions. Don't grant write or admin access for a read-only reporting task.
How is this different from a Mixpanel board or saved report?: Mixpanel boards and saved reports query live data against the models you maintain in Mixpanel — the right choice for governed, recurring product analytics. This approach is for a fast, shareable snapshot you can spin up in minutes and iterate by talking to Claude, then collect feedback on inline. Different jobs: one is a standing system, the other is a quick reviewable deliverable.