Data Cloud connectors at a glance
Data Cloud connectors, in preview in Gemini for business, let staff ask plain-language questions of live data in BigQuery, Spanner, AlloyDB, Cloud SQL and Looker. Queries run in place under each user's own permissions, and results can go into Docs, Gmail or Slides.
What changed with Data Cloud connectors
On November 6, 2026, Google Cloud announced Data Cloud connectors in Gemini for business, now in preview. Business users and analysts can ask questions in natural language and get answers from live enterprise data in BigQuery, in the operational databases Spanner, AlloyDB and Cloud SQL, and in governed Looker data, each listed as a preview. Results can then be turned into a Google Doc, a Gmail draft or a Google Slides deck.
For each question, Gemini searches Knowledge Catalog for candidate data and maps everyday business terms to specific tables and categories, using technical metadata, business glossaries and semantic models. It then writes SQL and runs it through the connector with the user's own credentials, so existing row- and column-level permissions still apply. The connectors use federated queries, leaving data where it is instead of copying or indexing it. Through BigQuery, they also reach open table formats such as Apache Iceberg, Delta Lake and Parquet, and cross-cloud data in AWS or Azure.
Admins set up default read-only connections in the Gemini admin console, and users then enable the connector in Gemini. Google keeps Conversational Analytics agents, built and certified by data teams, as the option for scoped, governed analyses, while the connectors handle ad hoc questions. Compared with public or self-managed MCP servers, Google says its connectors add built-in agent skills for each data engine and a guided setup with managed authentication, with no MCP middleware or custom OAuth client, plus settings such as a default billing project for BigQuery queries. The post does not give pricing or a general availability date.
Why Data Cloud connectors matters for businesses
For companies already on Google Cloud, this could shrink the queue of small data requests that reach analysts, since staff can ask in Gemini and move the answer straight into a document or email. Answers depend on the catalog behind them, though. Agencies setting this up for clients should clean up metadata, glossary terms and permissions first, and check answers against known reports before relying on them, especially while the feature is in preview.
Sources for this story
- Bringing conversational analytics to Gemini with Agentic Data Cloud connectors (opens in a new tab)Official
Google Cloud · cloud.google.com
Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.
- #google-cloud
- #gemini
- #bigquery
- #data-analytics
- #mcp
