This QuickStart shows how to connect Claude to Sigma using the Sigma MCP server and to Slack using the claude.ai Slack connector, then use both to query live Sigma data, format the results as a daily digest, and deliver it to a Slack channel or DM on a recurring schedule — automatically, with fresh data each time.

The workflow has two phases:

Along the way you'll learn how to:

For more information on Sigma's product release strategy, see Sigma product releases

If something doesn't work as expected, here's how to contact Sigma support

Target Audience

Analysts and data practitioners who use Sigma for data analysis and want to automate recurring data workflows. The design phase is entirely browser-based; scheduling requires Claude Code in a terminal.

Prerequisites

Footer

The Sigma MCP server is a remote connector that gives Claude the ability to search, explore, and query your Sigma organization. It authenticates using OAuth and inherits your existing Sigma account permissions — no additional credentials or API keys are required.

Step 1: Find your Sigma MCP URL

In Sigma, click your profile icon and navigate to Profile > MCP. Copy your personal MCP server URL:

Step 2: Add the connector in Claude

In claude.ai, click your profile icon and select Settings > Connectors > Add a custom connector:

Give it a name and paste the MCP URL copied from Sigma, then click Add:

Step 3: Connect and authenticate

Click Connect:

When prompted, enter your Sigma instance name and click Continue. Provide your Sigma credentials and log in.

When prompted by Claude, click Allow:

If successful, the Connect button will now show Configure.

Step 4: Configure permissions

Click Configure. By default, nothing is authorized. For testing, select Always allow at the top level to enable Claude to use all Sigma MCP tools without prompting each time:

For full setup details, see Use the Sigma MCP Server

Footer

We will demonstrate with Sigma sample data, but the workflow that is enabled can be applied to any type of data.

We will use a retail transaction dataset called PLUGS_ELECTRONICS.

Use case:
 You're on the sales operations team at a retail company. You want to start each morning with a Slack summary of sales performance without opening Sigma or building a dedicated dashboard.

The goal:
 Use Claude Code to query live data from Sigma, format the results as a daily sales digest, and deliver it to Slack automatically — once now to verify it works, then on a recurring schedule.

The data:
 All examples reference PLUGS_ELECTRONICS_HANDS_ON_LAB_DATA from the RETAIL schema. If your organization uses different data, the approach is identical — substitute your own connection and table names in the prompts.

Before Claude can query your data through the MCP, the data source must be enabled in Sigma's AI settings. This is a one-time administrator setup.

Enable PLUGS_ELECTRONICS as a data source

In Sigma, navigate to Administration > AI settings and select the Assistant tab. Click Add source, search for PLUGS, and select PLUGS_ELECTRONICS_HANDS_ON_LAB_DATA from the RETAIL schema:

Footer

With the Sigma MCP connected, start a new conversation in claude.ai and work through the following prompts in sequence.

Discover available data

Begin by confirming Plugs is accessible in your Sigma org:

Are you able to access the PLUGS_ELECTRONICS dataset?

Claude will call the Sigma MCP and reply with some details:

Run the sales summary query

With the data source confirmed, ask for the analysis:

Using the PLUGS_ELECTRONICS data in Sigma, give me a sales performance summary: the top 5 product categories by total revenue, along with transaction count and average order value for each. Use the most recent 30 days of data available.

Claude will query the live data and return a structured breakdown by category:

WHY IT MATTERS:
 Claude queries live data each time — not a snapshot or a cached result. When this runs on a schedule, the numbers always reflect your current data.

Footer

The raw analysis is useful, but for a Slack message it needs to be compact, scannable, and clearly formatted. Ask Claude to reformat it:

Format this as a Slack message for a daily sales digest. Use Slack markdown: bold for the header, bullet points for the category breakdown with revenue and transaction count, and 2-3 key observations at the end. Keep it under 400 words.

Claude will produce a Slack-ready message using Slack's markdown syntax (*bold*, bullet lists, etc.):

You can iterate on the format by following up in the same conversation:

Add a one-line summary at the top showing total revenue across all categories before the breakdown.

Once the format looks right, test delivery before setting up the schedule. In the same claude.ai conversation, prompt:

Send this message to me as a Slack DM.

Claude will use the Slack connector to locate your Slack user ID and deliver the message. Check your Slack DMs to confirm it arrived and the formatting renders correctly:


Once the format looks right and the test DM has arrived, the browser session has served its purpose — this is the design phase.

You've confirmed:

In the next section, you'll encode all of that into a scheduling prompt in Claude Code and hand it off to run automatically.

Footer

Scheduling requires Claude Code (at the time of this QuickStart) — the scheduling skill is not available in the claude.ai browser. If you haven't installed Claude Code yet, see Claude Code.

With the design confirmed in the browser, open a terminal and launch Claude Code.

We will use the /schedule command to describe the full workflow — Claude will load the scheduling skill and create the agent:

Create the schedule

The following command uses /schedule to describe the task:

/schedule every morning at 8am ET: query the PLUGS_ELECTRONICS data in Sigma for the top 5 product categories by total revenue over the last 30 days including transaction count and average order value, format the results as a Slack daily sales digest with a bold header and bullet points per category with 2-3 key observations, and send it as a Slack DM to [YOUR_SLACK_USERNAME_OR_CHANNEL].

Before creating the schedule, Claude will display a configuration summary for your review — showing the cron schedule, model, connectors, and other details:

Once confirmed, Claude creates the scheduled agent and returns a completion summary showing the trigger name, ID, schedule, next run time, connectors, and the steps it will execute each run:

Verify it works

Before waiting for the scheduled time, trigger an immediate run to confirm the full workflow end-to-end:

Send this manually now.

Claude will execute the workflow immediately. Check your Slack DM or channel to confirm the message arrived and the formatting renders correctly:

Manage the schedule

The completion summary includes a direct link to manage or disable the schedule:

https://claude.ai/code/scheduled/[your-trigger-id]

Open that URL to view the schedule details, update the instructions, or disable it:

Clicking into a Runs entry shows a log of every step Claude executed during that run:

Footer

This QuickStart demonstrated how to connect Claude to Sigma using the Sigma MCP and to Slack using the claude.ai Slack connector, then use both to automate a recurring data workflow — designed in the browser, scheduled via Claude Code.

The pattern is straightforward: Claude queries live Sigma data on a schedule, formats the result, and posts it to Slack — no dashboard to maintain, no pipeline to build, no manual steps once the schedule is running. The same approach applies to any recurring analytical question your team needs answered on a regular cadence.

Sigma brings the data governance, live querying, and organizational structure. Claude brings the reasoning, formatting, and ability to act. Together they make it possible to go from a question — "what were my top categories this month?" — to a formatted, delivered answer on a recurring schedule, without building a pipeline or maintaining a dashboard.

Additional Resource Links

Blog
Community
Help Center
QuickStarts

Be sure to check out all the latest developments at Sigma's First Friday Feature page!

   

Footer