drafty
Slack logo

Build a Slack channel-activity dashboard with Claude

Connect the Slack MCP server to Claude, ask for a channel-activity and weekly-digest dashboard from your real workspace, and publish it to a link your team comments on directly — no BI tool, no screenshots pasted back into Slack.

What you'll build
A self-contained workspace dashboard — messages this week vs. last, the most active channels, a daily-volume trend, top contributors, and a plain-language digest of what moved — generated by Claude from your real Slack data, then published to a drafty.im/canvas/… link. Your team clicks the exact tile 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

  1. The Slack MCP server gives Claude read access to your workspace — channels, messages, threads, members — through a controlled set of tools, honoring Slack's own permission model. You approve what it can touch through OAuth.
  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 Slack MCP server

Slack runs an official remote MCP server at https://mcp.slack.com/mcp. You connect once; it authenticates over OAuth, so no token is pasted into a config file. (Your workspace admin may need to approve MCP access first.)

In Claude Code:

claude
claude mcp add --transport http slack https://mcp.slack.com/mcp

Then run /mcp inside Claude Code and follow the OAuth prompt to authorize your workspace. When you authorize, grant read access only — this dashboard never needs to post messages or write to Slack.

In Claude Desktop: open Settings → Connectors → Add connector, find Slack, and complete the OAuth flow to connect your workspace.

Safety first
Connect with OAuth and grant the assistant read access to the channels you want reported on — nothing more. A dashboard reads message counts and activity; it has no reason to post, edit, or hold write permissions. Never paste a raw bot token (xoxb-…) into a committed config file. The MCP server honors Slack's permission model, so the assistant can only see what your account can see.

Step 2 — Pull the numbers

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

claude
Using the Slack MCP server, pull everything we need for a channel-activity dashboard for the last 7 days: total messages this week vs. the previous week, the 6 most active public channels by message count, daily message volume for each of the last 7 days, the count of active members who posted, and the top 5 contributors by messages sent. Then write a 3-bullet plain-language digest of what changed. Summarize the figures before you build anything.

Claude calls Slack, returns the figures, and you sanity-check them against what you see in the workspace before going further. This is the moment to catch a wrong assumption — a channel you forgot to include, bot messages inflating the count, a timezone that shifts the day boundary — 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. Total messages this week as the hero number with the week-over-week change, then tiles for active members and channels tracked, a bar chart of the top channels by message count, a 7-day daily-volume sparkline, a top-contributors list, and the 3-bullet digest at the bottom. 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:

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 active-members count looks low, are we counting threads replies?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant Slack 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 — count thread replies in the message total, not just root messages." 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 Slack when someone opens the link. For a weekly review or a Monday-morning digest, that's fine.

To make it a live canvas that always shows the current week's activity, copy this prompt — Claude sets up the refresh for you and schedules it to run on its own:

claude
Turn this Slack dashboard into a live canvas: every Monday morning, re-pull the latest 7 days of activity from Slack via the MCP server, rebuild the dashboard and digest, and push a new version to the same canvas URL so the link always shows the current week. Schedule it to run weekly on its own.

The link stays stable while the content updates underneath it — see keeping a canvas updated automatically.

What to watch for

Slack dashboard with Claude — FAQ

Do I need to paste my Slack token anywhere?
No. The remote Slack MCP server at mcp.slack.com authenticates over OAuth, so you authorize your workspace through a consent screen instead of pasting a token. Your workspace admin may need to approve MCP access first. Never paste a raw bot token (xoxb-…) into a config file or commit it to a repo.
Is the dashboard live or a snapshot?
A snapshot. It contains the activity Claude pulled when it built the file; it does not re-query Slack when someone opens the link. To refresh it, ask Claude to repull and re-push to the same URL — or put that on a weekly schedule so the stable link always shows the current week.
Can my team comment without a Slack 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 Slack needs access to the workspace.
Is it safe to give Claude access to my Slack workspace?
Connect with read access only, and a channel-activity dashboard never needs more than that. The MCP server honors Slack's own permission model, so the assistant can only see what your account can see, and in Claude you approve actions. Don't grant write or posting scopes for a read-only reporting task.
How is this different from Slack Analytics?
Slack's built-in Analytics gives you a fixed set of workspace metrics in Slack's own layout — the right choice for standing, admin-level reporting. This approach is for a fast, shareable snapshot you can shape however you want by talking to Claude — a custom digest for one team, a specific set of channels — then collect feedback on inline. Different jobs: one is a standing report, the other is a quick reviewable deliverable.