Build a Salesforce pipeline 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 Salesforce DX MCP server gives Claude read access to your org — opportunities, accounts, forecasts, users — through a controlled set of tools, including a SOQL query tool. It runs locally and uses the org you've already authorized with the Salesforce CLI; you pick which toolsets are exposed.
2. Claude runs the SOQL, 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 your sales leaders without losing their feedback to a screenshot circled in Preview.

Step 1 — Connect the Salesforce DX MCP server

Salesforce publishes an official MCP server, @salesforce/mcp. It runs locally via npx and talks to whatever org you've authorized with the Salesforce CLI — so no token is pasted into a config file.

First, authorize your org. Install the Salesforce CLI if you don't have it, then log in through the browser over OAuth:

Then add the MCP server to Claude Code, scoped to the data toolset so it can query but not deploy or modify metadata:

Run /mcp inside Claude Code to confirm it connected. The data toolset includes the run_soql_query tool — that's all this dashboard needs.

In Claude Desktop: open Settings → Connectors → Edit config, and add the same npx -y @salesforce/mcp --orgs DEFAULT_TARGET_ORG --toolsets data command as a custom MCP server.

Step 2 — Pull the numbers

Ask Claude in plain language. It uses the MCP server's run_soql_query tool to fetch real data from your org:

Claude runs the SOQL, returns the figures, and you sanity-check them against a Salesforce report before going further. This is the moment to catch a wrong assumption — a sandbox org, a custom fiscal calendar, opportunity records you didn't expect in the open set — 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 forecast-to-quota gap the most prominent thing on the page."
• "Color the pipeline bars by stage and show the deal count on each."
• "Flag the slipped deals in red in the opportunities table."

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 sales leaders open 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 stage bar, tile, or number they want changed and leaves a pinned comment — "this forecast looks high, are we excluding the deals stuck in Negotiation past their close date?" The comment is anchored to that element, not floating in a Slack thread. Claude reads the comments through the CLI, reruns the relevant SOQL 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 opportunities with a past close date from the weighted forecast." 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 Salesforce when someone opens the link. For a weekly pipeline 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:

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

What to watch for

• Read-only, always. A pipeline dashboard needs query access and nothing more. Scope the server to the data toolset and authorize a read-limited user.
• Check the figures before you share. The MCP returns exactly what your SOQL asks for — if your "open pipeline" query includes closed stages, or your forecast doesn't apply the probability weighting you expect, the dashboard will confidently show the wrong number. Reconcile against a Salesforce report 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.