Allows agents to use tabular files selected from Google Drive (Sheets, CSV, Excel, and Parquet) as data sources, synchronizing them into PostgreSQL for durable snapshots and governed queries.
Allows Google Sheets files to be synchronized into PostgreSQL as durable snapshots, which agents can discover and query through a governed semantic layer.
Serves as the managed destination for synced tabular data, storing durable snapshots that agents can query through Settra's governed semantic layer without raw SQL or source credentials.
Settra turns spreadsheet data into reusable Apps that deliver reliable mini BI reports. Build an App once with AI, then run the same trusted logic in Settra, in chat, or on a schedule.
People and AI agents work from the same data, business rules, and outputs, so answers stay consistent wherever work happens.
Build with AI. Describe the App you need and turn spreadsheet data into something useful in minutes.
Build by hand. Start from raw data and define the logic, calculations, and outputs exactly the way your team needs them.
Reuse it everywhere. Use the same App in Settra, in chat with your AI assistant, or on a schedule.
Trust every answer. Keep business rules and calculations with the App so people and agents do not have to reinterpret them every time.
Stay ahead of change. See which Apps a spreadsheet change could affect before a renamed, removed, or changed column breaks them.
Related MCP server: mcp-data-lens
Connect a Google Sheet, CSV, Excel, or Parquet file from Google Drive.
Build the analysis, calculations, and outputs you need with AI.
Run the App yourself or let an AI agent discover, build, and run it for you.
Settra keeps each App reusable and understandable, so a workflow started by a person can be continued by an agent—and vice versa.
Settra is open source under the Apache License 2.0. Use the managed service or run it in your own infrastructure.
For questions or support, visit settra.io/support.
This server cannot be deployed
The all-in-one data stack for agents. Upload files, run SQL, evolve tables, and render charts.
The grounded data layer for any LLM: governed SQL, metrics, lineage and catalog over your data.
Query your warehouse or a CSV with Claude/ChatGPT over MCP, governed by table-level ACL + audit.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
