Tableau MCP for AI Agents. Query all dashboards and audit BI metadata via chat.
Tableau MCP lets your AI client query and analyze complex business intelligence directly through conversation. Access workbook metadata, audit data source freshness, list users, and get summarized insights from dashboards without ever leaving your chat window.
Give Claude and any AI agent real-world access
Your agent retrieves a searchable index of all Tableau workbooks within the connected site.
You can ask for data or rendered images from particular dashboards, going deeper than just looking at the front end.
This tool lists published data sources, showing crucial details like when they last refreshed and if they're connected properly.
List all active projects and sites within the Tableau environment to understand the organizational hierarchy.
Query details about site users, including their group membership and assigned permissions.
Review the status of scheduled extract refresh jobs and other background tasks to ensure data integrity.
Ask an AI about this
Waiting for input…
What AI agents can do with Tableau: 7 Available Tools for Metadata Management
Use these tools with your agent to manage metadata, check data integrity, and retrieve structured information about the entire Tableau environment.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Tableau MCPList Workbooks
Retrieves a list of all available Tableau workbooks on the platform.
Get Workbook
Fetches detailed metadata for a specific workbook by name or ID.
List Views
Lists all available dashboards and views in the site, useful for finding specific...
List Datasources
Provides a list of published data sources, including crucial metadata like refresh...
List Projects
Retrieves the names and structure of all projects within the connected Tableau site.
List Users
Lists all registered users in the Tableau environment for auditing purposes.
List Jobs
Checks and lists background data processing jobs, showing their current status (running, failed, complete).
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on each call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Tableau, then connect any of our 5,200+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,200+ others, all in one place
- Add new capabilities to your AI anytime you want
- Connections are secured and governed automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog weekly
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Tableau. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on each call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
The Pain of the Dashboard Deep Dive Solved with Vinkius AI Gateway
Right now, finding a single piece of data often feels like archaeology. You have to navigate through project folders, open three different workbooks just to compare two KPIs, and then manually check the settings menu every time you suspect the source might be old. It's tedious clicking and constant context switching.
With this MCP, your agent handles all that navigation for you. Instead of opening 15 tabs and cross-referencing dates, you ask one question—like 'Show me the revenue trend vs. the goal.' The answer comes back with immediate, structured insights without ever leaving your chat window.
Tableau MCP: Metadata on Demand
The biggest time sinks are checking permissions and data health. You currently have to log into the administration panel just to see if a specific user is still active or if the key financial metrics were pulled yesterday or last week.
Now, you can audit everything in conversation. Tools like `list_users` give instant access to membership details, while `list_datasources` tells you exactly how stale your data is—all without logging into a single admin page.
What your AI can actually do with this
Stop clicking through menus just to find a dashboard metric or check if the underlying data is current. This MCP connects your AI client straight into Tableau Cloud and Server, letting you explore business intelligence using natural language prompts. You can ask for summaries of KPIs, list all existing workbooks in a project, or even query specific views on a dashboard.
It’s like having an admin who knows every corner of the BI system but talks to you instead of sending tickets. Need to check if data sources are stale? Ask it. Want to know which users have access to what? Just ask. Vinkius hosts this MCP, meaning you connect once and gain immediate access to all these powerful analytics tools alongside your other professional services.
019d760f-e5bc-7201-84da-d6226e8a1898 Here's how it actually works
The bottom line is your agent handles all the complex API calls needed to pull deep BI data into a simple chat response.
Connect your AI client through Vinkius, granting it read-only access to your Tableau Cloud or Server instance.
Give your agent a natural language prompt—for example, 'What data sources failed to refresh in the last 24 hours?'
The MCP executes the necessary calls and returns structured metadata, such as job status, user lists, or dashboard summaries.
Who is this actually for?
Data analysts and engineers who hate clicking through dashboard portals. This MCP is for anyone whose job requires monitoring metrics, auditing permissions, or finding specific reports without manual navigation.
Finds and explores dashboards by simply asking questions about KPIs instead of navigating the full Tableau menu structure.
Monitors extract job status and data source freshness through chat, immediately identifying stale or failed connections.
Audits complex data source connections, checks refresh schedules, and verifies user permissions across the entire site structure.
What Changes When You Connect
Instantly check data freshness. Instead of navigating to every single data source connection, you simply ask the agent which sources haven't refreshed recently, saving hours of manual auditing work.
Audit user permissions quickly. Need to know who has access to a specific dashboard? Use the tool to list site users and their roles without ever logging into the admin console.
Understand your BI scope immediately. You can use tools like list_workbooks or list_views to get an index of everything available, letting you understand the project structure before deep diving into data.
Keep track of scheduled processes. If a critical dashboard relies on nightly data loads, the MCP lets you list jobs and see if background tasks succeeded or failed overnight.
Get context-aware summaries. You don't just get raw data; your agent reads metadata to give you actionable summaries about what reports exist and where they live.
See it in action
Identifying stale metrics before a meeting
A Data Analyst needs to confirm if the 'Q3 Sales Dashboard' is using current data. Instead of opening Tableau, going to the data source tab, and checking multiple dates manually, they ask their agent, which uses list_datasources and job monitoring tools to report stale sources in seconds.
Onboarding a new team member
A BI Admin needs to verify who can see the executive reports. They use the MCP to list site users, quickly cross-referencing roles and permissions without needing manual helpdesk support or walking through the UI.
Troubleshooting dashboard failures
A Data Engineer discovers a key KPI is showing incorrect data. Instead of guessing, they ask their agent to list jobs. The MCP reveals that the scheduled extract refresh job failed 3 hours ago and provides details on why.
Mapping out project scope
A Project Manager needs a full inventory of available reporting assets. They prompt the agent, which executes list_workbooks and list_projects, providing an immediate, structured list of every report asset in the entire organization.
The honest tradeoffs
What to watch out for, and the recommended way to handle each one.
Manually checking data sources
The user opens Tableau, navigates to the Data Sources menu, and clicks through dozens of connection tabs, spending 20 minutes trying to find a single source that hasn't refreshed.
Just ask your agent. Using list_datasources lets you query data freshness immediately. Your prompt should be: 'Which published data sources need attention?'
Guessing which dashboard to check
A user doesn't know if the KPI they need is in a workbook or a specific view and spends time clicking through project folders just to find the right starting point.
Start by listing everything. Use list_workbooks first to see all assets, then use list_views if you suspect it's a dashboard-specific query.
Assuming job completion
A manager assumes that because the report exists, the data must be current and ready. They find the workbook but don't realize the background refresh failed.
Always verify the process. Use list_jobs to check the status of extract refreshes before trusting any numbers you see.
When It Fits, When It Doesn't
Use this MCP if your primary bottleneck is information retrieval, not data creation. If your job involves auditing who can see what, checking when underlying metrics were last updated, or getting an inventory count of report assets (workbooks, views, projects), this is essential. It's a metadata powerhouse.
Don't use it if you need to modify the underlying data structure, write complex calculated fields within Tableau, or build entirely new dashboards from scratch. For those tasks, stick with the dedicated BI tool UI. This MCP is for asking questions about the existing system, not for rebuilding it.
Questions you might have
How do I use the Tableau MCP to check if my dashboards are up-to-date? +
You need to query the system for job status. Use list_datasources to see when a source last refreshed, and then use list_jobs to monitor the actual background task success or failure.
Can I list all my projects using the Tableau MCP? +
Yes, you can. Use the list_projects tool to retrieve a structured overview of every project available in your site's hierarchy.
What if I want to know who has access to a specific workbook? Is it possible with Tableau MCP? +
You can audit user roles using the list_users tool. This gives you membership and role details, helping you understand site access permissions.
Does the Tableau MCP let me see every dashboard in one place? +
The list_views tool provides an index of all views (dashboards). You can use this to find a starting point for your data exploration via chat prompts.
Is the Tableau MCP suitable for technical users or just executives? +
It serves both. Engineers use it to check list_jobs and connections, while executives can simply ask their agent for a summary of KPIs from available workbooks.