MCP connectorsTableau

Tableau MCP: connect Tableau to Claude and ChatGPT

Ask Claude or ChatGPT what sales were last week, which region is behind target or why a number moved since last month. The answer comes from the figures behind your Tableau dashboards, in plain words, without opening a workbook and setting the filters.

We build the connector for your company on Tableau’s own API. Each person connects as their own Tableau user, so the AI sees the workbooks and data that person may see, and it only reads.

Built for your company · Works in Claude, ChatGPT and Copilot

In practice

What your team can do with Tableau in Claude and ChatGPT

Managers

The number before the meeting

This week’s figure from the dashboard you already trust, compared with last week, in one sentence you can read on the way in.
Sales leaders

Which region is behind

Revenue or pipeline per region, team or product from the sales dashboard, with the ones under target named.
Analysts

Fewer one-off requests

Colleagues get the simple numbers themselves, from the views you built, and you keep your time for the questions that need an analyst.
Everyone

Find the right dashboard

Which workbook holds churn, who owns it and when it was last updated, instead of asking around.
Examples

Ask it like this

  • “What were total sales last week according to the Sales Overview dashboard?”

  • “Which region is furthest behind target this quarter?”

  • “Which dashboard shows customer churn, and who owns it?”

  • “Compare support ticket volume for September and October.”

  • “What are the top five products by revenue in the Chicago store this month?”

  • “Summarise the Weekly Operations dashboard in five lines for the management meeting.”

The connector

What we build for Tableau

Deployed OS has no ready Tableau connector yet. We build it for your company when you start, on Tableau’s own API, with the same rules as every other connector: each person’s own login, access decided by group, every call logged.

Workbooks and views
The projects, workbooks and views a person can see, with owner and when each was last updated.
The figures behind a view
The data a view shows, read as numbers with the filters you ask for, so the answer matches the dashboard.
Data sources
Published data sources with their fields, and when the data was last refreshed.
Search
Finding the right workbook or view by name or topic when you do not know where it lives.
Your own definitions
Which dashboard is the source for which key figure in your company, so the AI answers from the one you have agreed on.
Security

Who sees what

Read-only
The connector reads. It does not publish, edit or delete workbooks, and it does not change data sources or permissions. We only build write actions if you ask for them.
Each person’s own Tableau user
Everyone connects as themselves, and Tableau applies that user’s permissions to every call. Someone who cannot open the finance project in Tableau does not get its numbers through the AI either.
Your company decides who gets it
Admins choose which groups get Tableau in Deployed OS. A group without access never sees the connector.
Every call logged
Who asked, what was read and when. Deployed OS keeps the log, and it can be exported.
Setup

Set up the Tableau connector in three steps

01
We go through with you which questions matter most and which dashboards answer them, and build the connector on Tableau’s API.
02
Your Tableau administrator approves the connection, and you choose which groups get Tableau in Deployed OS.
03
Each person connects their own Tableau user. From then on they just ask.
Compared

Tableau’s own MCP server or Deployed OS?

Tableau has its own Tableau MCP. It is open source to run yourselves against Tableau Server or Tableau Cloud, and Tableau also hosts a version for Tableau Cloud where each user signs in as themselves. If Tableau is the only system your team wants in its AI tool, it is a good place to start.

Deployed OS is for when Tableau is one system among several. It sits next to your CRM, finance system and other tools in one company connection, admins decide which groups get each system, every call is logged in one place, and the same rules apply in Claude and ChatGPT. We also build tools around your own dashboards and key figures, so people get the agreed number.

Their documentation: Tableau MCP

Questions

Tableau MCP: common questions

Yes. Tableau publishes Tableau MCP as open source and hosts a version for Tableau Cloud. Deployed OS adds Tableau to one company connection with your other systems, with access per group, one log and tools built for your company.

No. The connector reads workbooks, views, data sources and the figures behind a view. It does not publish or edit anything, and we only build write actions if you ask for them.

Yes. Everyone connects as their own Tableau user, and Tableau checks every call against that user’s permissions. The AI cannot see more than the person could in Tableau.

Both have the API we build on. For Tableau Server, the server needs to be reachable from Deployed OS, which we go through with your IT team first.

Deployed is an EU company and fully GDPR compliant, and you choose where your data is stored, down to the city. Tableau data is fetched when someone asks for it.

It depends on the size of your team. Get in touch and we will walk you through it.

More connectorsAll connectors
Let’s talk

See it on your own tools.

Tell us which systems your company runs on. We’ll show you what your team can ask, and what IT gets to control.