- MAPPING
- AUDIT
- CLEANUP
- HUMAN
Short answer
How can I map my Sigma data lineage using AI?
Your AI uses the Sigma MCP to pull a list of your datasets and their specific database connections. This lets you see exactly which underlying sources feed your specific Sigma models. You get a clear map of your data architecture.
The results of your audit
Where your data connections land
Tracing lineage turns disconnected datasets into a visible map.
MAPPING
Visualized data paths
The AI identifies which database connections power which datasets. You get a clear view of your data flow.
AUDIT
Source verification
Confirm that your Sigma datasets are pulling from the correct production databases. This prevents reporting errors.
CLEANUP
Identify unused links
Find datasets that are connected to stale or redundant database sources. You can then prune your environment.
HUMAN
Manual architecture review
The AI identifies the connections, but you decide if the logic matches your business requirements. You handle the final structural changes.
The workflow
What your AI does when the request arrives.
The AI moves from broad discovery to specific connection mapping.
Inventory datasets
The AI scans your Sigma environment to find all available datasets.
list_datasetsIdentify connections
The AI pulls the list of active database connections used in your workspace.
list_connectionsCross-reference sources
The AI matches specific datasets to their corresponding database connections to build the lineage.
list_datasetslist_connectionsReport findings
The AI presents a structured summary of the relationships it found between your data and your sources.
list_datasets
Try it
Copy these to start.
Use these prompts to begin your audit.
Starting points
These are starting points. Swap out the specific dataset names or connection IDs for the ones you actually use in Sigma.
Sigma Computing Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_gQm7h5oIY5gOVePr0VgifFP0jBzhq0ebXuCRDTAj/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Sigma Computing capabilities are ready to use.
{
"mcpServers": {
"sigma-computing-mcp": {
"url": "https://edge.vinkius.com/vk_preview_gQm7h5oIY5gOVePr0VgifFP0jBzhq0ebXuCRDTAj/mcp"
}
}
}List all my Sigma datasets and tell me which database connections they use.
Which datasets are currently connected to the 'Sales_Production' database?
Find the connection details for the 'Monthly_Revenue_Report' dataset.
Show me a list of all active connections in my Sigma workspace.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Sigma Computing once, then ask.
Just link your Sigma account. Your credentials stay encrypted, and you can immediately start asking questions about your data structure.
Connect Sigma Computing to your AIFAQ
How this task behaves
- 01
Can the AI change my Sigma dataset settings?
No. The AI can only read your datasets and connections. It cannot modify, delete, or create new Sigma objects.
- 02
Can the AI see the actual data inside my tables?
No. The AI only sees the metadata, such as dataset names and connection IDs. It does not access the rows of data within your tables.
- 03
Does this work with any database?
It works with any database that is already established as a connection within your Sigma workspace.
- 04
Can the AI fix a broken connection?
No. The AI can identify which connection is being used, but you must fix the connection manually in Sigma.
- 05
How does the AI know which dataset belongs to which connection?
The AI uses the list of datasets and the list of connections to map the relationships defined in your Sigma environment.
More questions about Sigma Computing? The Connector page answers them. See everything the Sigma Computing Connector can do
Connect Sigma Computing to Claude, Cursor, ChatGPT & more
