Tableau MCP Server
Connect to the Tableau MCP server to browse dashboards, query published data sources, export views, and surface Pulse metric insights using AI agents on Gumloop, Claude, or Cursor.
Try Tableau now
Type what you want done. Sign in and run it live with an AI agent.
|
Tableau
Installation
Get StartedCreate a Gumloop Account
To use this MCP, you need a Gumloop account. If you don't have one yet, you can create one for free.
Copy Your Server URL
Copy your MCP server URL and add it to your client. You'll be prompted to authorize on first use.
Tools (15)
List Views
List all views on a Tableau site with optional filtering. Returns view metadata including name, owner, workbook, and usage statistics.
List Custom Views
List custom views on a Tableau site. Custom views preserve saved filters and other user customizations.
Get View Data
Retrieves data in CSV format for a view or custom view. Use custom_view_id to get data with saved filters preserved.
Get View Image
Retrieves an image of a view or custom view. Default size is 800x800 pixels. Use custom_view_id to get image with saved filters preserved.
List Workbooks
List all workbooks on a Tableau site with optional filtering. Returns workbook metadata including name, description, project, owner, and views.
Get Workbook
Retrieves information about a specific workbook, including views contained in the workbook.
List Datasources
List all published data sources on a Tableau site with optional filtering.
Search Content
Search across all supported content types (workbooks, views, datasources, projects, etc.) for objects matching the search expression.
List All Pulse Metric Definitions
List all Pulse Metric Definitions on the current site. Pulse metrics provide automated insights.
List Pulse Metrics From Definition Id
List all Pulse Metrics for a specific Pulse Metric Definition.
List Pulse Metrics From Metric Ids
Retrieve Pulse Metrics by their IDs. Useful for getting details of specific metrics.
List Pulse Metric Subscriptions
List all Pulse Metric Subscriptions for the current user.
What is Tableau MCP?
The Tableau MCP server gives AI agents secure read access to your Tableau Cloud or Tableau Server content. That means agents can browse views and workbooks, export a dashboard as an image or CSV, run structured queries against published data sources, search across all your content, and pull Tableau Pulse metrics and AI insight bundles. The server connects to the same analytics your team already relies on, so an agent can answer questions about your data instead of just pointing you to a dashboard.
Analysts and data teams spend a lot of time exporting views, copying numbers out of dashboards, and re-running the same queries for whoever asks. The Tableau MCP server hands those tasks to an AI agent that knows how to read your views, query your data sources, and summarize your Pulse metrics. Describe what you need, and your AI agent will pull the numbers and the visuals for you.
MCP stands for Model Context Protocol, an open standard that lets AI agents call external tools. Normally, working with the Tableau REST and VizQL APIs means generating a Personal Access Token, managing a session token, and tracking your site ID across calls. Gumloop wraps all of that behind a hosted server: add your Tableau Personal Access Token once. After that, you can browse dashboards, query data sources, and read Pulse metrics just by asking your AI agent in plain language.
Related MCP servers
Looker MCP Server
Interact with Looker Enterprise dashboards and analytics content
Sigma Computing MCP Server
Interact with Sigma Computing to manage workbooks, members, teams, workspaces, and data connections
Hex MCP Server
Interact with Hex to manage projects, runs, collections, data connections, users, and groups
Google BigQuery MCP Server
Query and manage BigQuery datasets, tables, and execute SQL
Snowflake MCP Server
Interact with Snowflake data warehouse for executing SQL queries, managing tables/databases, and accessing data
Google Sheets MCP Server
Read, write and update your Google Sheets
What you can do with Tableau MCP on Gumloop
Browse and filter dashboards and views
List views filtered by name, owner, project, tags, or popularity, and list custom views by name or owner, so an agent can find the right dashboard fast.
Export views as images or data
Render any dashboard as a PNG snapshot or pull the underlying data as CSV, with runtime filters and custom pixel dimensions for the image, for automated reports and digests.
Explore workbooks
List workbooks across your site and drill into the views each one contains.
Query published data sources
Run structured analytical queries through the VizQL Data Service: select fields, apply filters, aggregate (SUM, AVG, COUNT, MEDIAN, and more), group by date, sort, and add calculated fields. It is SQL-like power without writing SQL.
Inspect data source metadata
Retrieve field names, data types, and roles from a published data source before querying it.
Search across all your Tableau content
Run full-text search over views, workbooks, data sources, projects, flows, and more.
Track Pulse metrics
Browse metric definitions, retrieve current metric values, and see which KPIs you are subscribed to.
Generate Pulse AI insight bundles
Produce AI-generated narratives for a Pulse metric, including the current value, trends, and automated insights, at multiple detail levels from a headline number to a full breakdown.
How to connect the Gumloop Tableau MCP Server
- 1
Create a free Gumloop account
Sign up at gumloop.com. No credit card required.
- 2
Add the Tableau MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Tableau in your AI workflows
That's it. Your AI agent can now browse views, query data sources, export dashboards, and read your Pulse metrics. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Tableau MCP use cases
Automated dashboard digests for leadership
An agent exports the latest view as a PNG and the underlying CSV on a schedule, then posts the snapshot and a short written summary to Slack or email, so executives can see the numbers without opening Tableau.
Self-serve KPI answers for RevOps
When someone asks for a figure, an agent queries the published data source directly through VizQL, aggregates the result, and replies with the number, instead of waiting on an analyst to build a one-off view.
Pulse insight summaries for analytics teams
An agent generates AI insight bundles for the team’s key Pulse metrics, captures the trends and anomalies, and writes a weekly roundup into Notion or a Google Doc.
Data source audits for data teams
An agent searches all content, lists published data sources, and pulls field-level metadata to map what exists and which sources back which dashboards.
Weekly metric reports for marketers
An agent pulls view data as CSV, charts the week-over-week change, and delivers a formatted report, chaining Tableau with Sheets and Slack in one run.
Why use Gumloop for Tableau MCP
Add your token once, no code
Working with the Tableau APIs directly means generating a Personal Access Token, exchanging it for a session token, and tracking your site ID across calls. With Gumloop you add your Personal Access Token one time and it is stored securely. No env vars, no token management, no code.
Works with multiple MCP clients
Use the same hosted Tableau MCP server in Gumloop, Claude, Cursor, and other MCP-compatible clients. Same server URL, works with any MCP client.
Chain Tableau with 100+ integrations
An agent can pull a metric from Tableau, format it, and write it to Slack, Notion, Google Sheets, or your CRM in a single run.
Enterprise-grade hosting
Gumloop hosts the server for you and respects your existing Tableau access controls. See trust.gumloop.com for security details.
Free to start
Gumloop has a free tier so you can try the Tableau MCP server at no cost. Paid plans start at $37/month.
Frequently asked questions
Ship Tableau agents in minutes
Connect any AI agent to 100+ MCP servers, fully hosted, zero setup.