The Tableau Next Model Context Protocol (MCP) Beta Server is a companion to the
generally available Tableau Next MCP Server. It gives you early access to tools that create,
update, and delete dashboards, semantic models, visualizations, and alerts before they reach
general availability.
Note Tableau Next MCP Beta Server is a pilot or beta service that is subject to the Beta
Services Terms at Agreements - Salesforce.com or a written Unified
Pilot Agreement if executed by Customer, and applicable terms in the Product Terms
Directory. Use of this pilot or beta service is at the Customer's sole
discretion.
How the Beta Server Differs from the Generally Available Server
The generally available Tableau Next MCP Server connects your AI agent to Tableau Next for
querying and discovery. It lets your agent (whether Claude, ChatGPT, Slackbot, or any
MCP-compatible client) ask questions in natural language, retrieve metadata, and explore
your analytical assets, but it can't create or modify Tableau Next assets.
The beta server adds tools that create, update, and delete Tableau Next assets, including
dashboards, semantic models, visualizations, and alerts. You can use both servers at the
same time in the same org.
When to Use Each MCP Server
Use the generally available (GA) MCP server when you need production-ready access to
Tableau Next across your org. It lets your agents ask questions, retrieve metadata, browse
assets, and run analytics.
Use the beta MCP server to experiment with building and editing Tableau Next assets:
create dashboards, update semantic models, set up alerts, or optimize your semantic model
for AI consumption. These tools are new and still under active development, so use them
with discretion.
A common practice is to run the beta server on a sandbox or personal org while using the
GA server for broad distribution across your company.
Some situations where the beta server adds value:
You want to build a dashboard or visualization from scratch, without opening the
Tableau Next editor.
You're managing semantic models at scale and want to create, update, or delete data
objects, metrics, and relationships directly from your AI agent.
You want to monitor a key metric and have alerts sent automatically when it changes, in
your flow of work.
You're setting up a new workspace and want to create data objects from a file upload or
a Snowflake connection.
You want to optimize how your AI agent understands your data by auto-generating
metadata descriptions or running accuracy tests.
Setup and Licensing
Setup and licensing for the beta server are similar to the generally available server.
Follow the steps in enable Tableau Next MCP (MCP) Server, and select
Tableau Next Beta from the servers list.
We use three kinds of cookies on our websites: required, functional, and advertising. You can choose whether functional and advertising cookies apply. Click on the different cookie categories to find out more about each category and to change the default settings.
Privacy Statement
Required Cookies
Always Active
Required cookies are necessary for basic website functionality. Some examples include: session cookies needed to transmit the website, authentication cookies, and security cookies.
Functional Cookies
Functional cookies enhance functions, performance, and services on the website. Some examples include: cookies used to analyze site traffic, cookies used for market research, and cookies used to display advertising that is not directed to a particular individual.
Advertising Cookies
Advertising cookies track activity across websites in order to understand a viewer’s interests, and direct them specific marketing. Some examples include: cookies used for remarketing, or interest-based advertising.
