Sigma Computing MCP for AI Agents. Audit Data Lineage and Connections on Demand
Sigma Computing MCP equips your AI agent to audit and map your entire BI environment without opening a browser. List every workbook, trace datasets back to their source connections, and see who owns which team or dashboard—all by asking natural language questions. It turns complex data lineage auditing from hours of clicking into simple conversation.
Give Claude and any AI agent real-world access
List all available dashboards, check specific dashboard details, or list the individual pages within any given workbook.
Discover every dataset available in your organization and map out all configured data source connections used across Sigma.
List every user account within the organization or retrieve a complete list of defined teams for governance checks.
Ask an AI about this
Waiting for input…
What AI agents can do with Sigma Computing: 7 Tools for Data Auditing
These tools let you query the metadata of your entire Sigma environment to audit workbooks, datasets, and user accounts.
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 Sigma Computing MCPList Workbooks
Retrieves and lists all available dashboards within your Sigma organization.
Get Workbook Details
Pulls specific, detailed information about a single dashboard you identify by its ID...
List Workbook Pages
Shows all the individual pages contained inside a specified workbook.
List Connections
Provides a list of every data source connection that has been configured in Sigma.
List Organization Members
Lists all user accounts currently registered within the entire Sigma organization.
List Organization Teams
Retrieves a list of every defined team structure in the organization for reporting and auditing purposes.
List Datasets
Lists all available datasets that have been created or indexed across the entire Sigma environment.
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 Sigma Computing, 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 Sigma Computing. 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 Headache of Data Discovery Solved with Vinkius AI Gateway
Today, finding out what data exists across a large organization is painful. You start by logging into the BI platform and clicking through dashboards one by one. You copy names, you open tabs to check dependencies, and you spend hours cross-referencing spreadsheets just to map out who owns which metrics or where the source files are.
With this MCP, that manual process vanishes. Your agent interrogates Sigma’s metadata directly. Instead of clicking through a hundred dashboards, your agent uses `list_workbooks` to give you an instant inventory and then maps dependencies using natural conversation.
Sigma Computing MCP: See the Full Picture
You no longer have to manually check user directories, data source connections, or team structures one by one. Your agent can consolidate all that information—from running `list_organization_members` to checking every configured pipe via `list_connections`—into a single, actionable report.
It means you get definitive architectural documentation instantly. You stop guessing and start knowing exactly how your company's data is organized.
What your AI can actually do with this
This MCP lets your AI agent act like an internal data steward for Sigma Computing. You don't have to manually navigate heavy BI platforms just to understand what data exists or where it came from. Instead, you can ask questions that interrogate the metadata itself. Need to know which datasets feed into a dashboard? Ask.
Want to map out all the connections between Snowflake and BigQuery used across your organization? Ask that too.
The agent treats the platform like an API endpoint you can talk to. You'll get visibility by using Vinkius, connecting this MCP directly to your preferred AI client. It lets you pull reports on user structures—seeing which teams exist or who belongs where—and mapping out every workbook and page without leaving your console.
Your agent becomes a powerful tool for data governance and architectural auditing.
019d7607-ef5a-72e7-a501-546c2cb1718c Here's how it actually works
The bottom line is that you get an AI-driven view of your entire data ecosystem's architecture without ever needing to log into the Sigma UI.
Anchor this MCP directly into your AI agent framework.
Securely store your Sigma Client ID and Secret pairing inside the workspace to keep credentials locked down.
Prompt your agent with a complex question, like 'List all BI workbooks related to Q3 sales and show me what datasets they depend on.'
Who is this actually for?
The Data Architect who has to audit dependencies before a migration. The BI Developer stuck tracing report sources across multiple teams. Or the Governance Manager who needs to confirm user access and team structures quickly.
Uses this MCP to find out which dashboard was built using a specific dataset without having to ask a teammate or manually search through hundreds of workbooks.
Maps the entire data flow by listing connections and checking dependencies between datasets, ensuring no critical source is missed during an infrastructure upgrade.
Uses it to list all available workbooks for a project area, then drills down using get_workbook_details to find the exact page structure needed for a new report build.
What Changes When You Connect
You can map out data dependencies immediately. Instead of clicking through dozens of dashboards, your agent uses list_workbooks to find all relevant reports, then checks the underlying source with get_workbook_details.
Gain complete visibility into your data sources. Use list_datasets and list_connections together to trace exactly where every piece of information in Sigma originates from—critical for governance.
Stop guessing about user access. Your agent uses list_organization_members and list_organization_teams to pull a definitive list of users and team boundaries, instantly solving onboarding roadblocks.
Understand dashboard architecture quickly. You can run list_workbook_pages on a target workbook to see the exact page layout without having to manually navigate into the live editor.
Audit data governance from your IDE. The MCP allows you to treat metadata discovery as a conversation, dramatically reducing the time spent piecing together complex lineage paths.
See it in action
Tracing a Missing Metric
A BI Developer notices one key metric is suddenly wrong. They prompt their agent: 'List all workbooks related to the North American region and see what underlying datasets they depend on.' The agent executes list_workbooks and then uses get_workbook_details to pinpoint the exact workbook that has broken dependencies, saving hours of investigation.
Compliance Audit Prep
The Governance Manager needs to prove who can access sensitive data. They prompt their agent: 'List all datasets and show me which teams are associated with them.' The tool uses list_datasets cross-referenced with list_organization_teams, creating an instant audit trail.
Onboarding New Analysts
A new analyst needs to know the scope of available data. They ask their agent: 'What datasets are available in this organization?' The tool runs list_datasets immediately, providing a full inventory without needing help from an existing team member.
Infrastructure Migration Check
The Data Architect is migrating the backend data warehouse. They prompt their agent: 'Show me all connections used across Sigma.' The tool runs list_connections, giving them a definitive list of every source they must account for in the migration plan.
The honest tradeoffs
What to watch out for, and the recommended way to handle each one.
Manually Checking Dependencies
A user has to open 15 different dashboards, click into each one, and manually navigate through tabs and source lists just to see what data is used.
Instead of clicking around, prompt your agent: 'List all workbooks related to Q3 sales.' The tool runs list_workbooks and then checks the dependencies using get_workbook_details, providing a consolidated report in one go.
Relying on Memory
A team member remembers that 'Dataset X' was used, but can't recall which workbook it belongs to or who owns the source connection.
Ask your agent: 'List all datasets and show me their connections.' The tool uses list_datasets combined with list_connections, giving you a complete map of data ownership.
Searching by Title Only
A user searches for dashboards containing the word 'finance' but misses critical layouts because they don't know all possible naming conventions.
Run list_workbooks first. Then, if needed, use list_workbook_pages on a specific result to drill down and confirm that the dashboard contains the right information.
When It Fits, When It Doesn't
Use this MCP if your primary goal is discovery, auditing, or mapping data architecture. If you need to understand what dashboards exist, where their data comes from (connections/datasets), or who owns them (users/teams), this tool is essential. It's your metadata reconnaissance unit.
Don't use it if you just want to view a single report and interact with the native Sigma UI features—for that, stick to the standard client connection. Also, don't use it if you only need to run simple user reports; the dedicated list_organization_members tool is enough for basic directory checks.
This MCP shines when you need to connect disparate pieces of information: 'Show me the users (list_organization_members) who own dashboards that rely on datasets from this specific connection (list_connections).'
Questions you might have
How does the Sigma Computing MCP help me find datasets? +
The MCP uses the list_datasets tool to provide a complete list of all indexed datasets in the organization. This gives you an immediate inventory and helps you know what data is available for analysis.
Can I see which users are on specific teams using the Sigma Computing MCP? +
Yes, by running list_organization_teams to get the team roster, and then cross-referencing that with the output of list_organization_members. This helps you map out your organizational structure.
What is the best way to check a dashboard's source connections? +
You can first use list_workbooks to find the ID, then run get_workbook_details on that specific workbook. This reveals details about its underlying data sources and dependencies.
Does the Sigma Computing MCP help me audit connections? +
Absolutely. The list_connections tool pulls a list of every configured data source connection, allowing you to conduct a full audit of all backend pipes used by your BI reports.
Is the Sigma Computing MCP only for viewing dashboards? +
No. Beyond workbooks, it also manages user topology via list_organization_members and helps map out core datasets using list_datasets, making it a full governance tool.