Google announced QueryData support for Firestore with MongoDB compatibility on October 12, 2026. Google says the feature lets developers build data agents that query database content through conversational language. Its documentation says QueryData translates natural-language questions into MongoDB-compatible Query Language (MQL) queries, using developer-supplied context sets with database-specific information. The feature is in preview, with potentially limited support. Sources: Firebase, Google Cloud
NewsEditorialSource: Firebase
Google adds QueryData preview to Firestore with MongoDB compatibility
Why it matters
Developers should evaluate it with an isolated test database and validate generated queries. They should also assess authorization before exposing an agent to users. The supplied sources do not include independent testing of functionality or accuracy.
Attribution
Sources
- 1FirebaseRelease NotesSource published (UTC)
- 2Google CloudQuery databases in natural language with QueryData
- 3Google CloudIntegrate QueryData with an application
Read the original source for full details and context.
EditorialSource: Oracle
Oracle adds managed MCP server support for OCI Database Services
Oracle added managed MCP server support for OCI Database Services on October 13, 2026, according to its release notes. The interface lets MCP-compatible AI agents and applications inspect database resources through read-only operations; it cannot modify those resources. It supports four services: Base Database Service, Exadata Database Service on Cloud@Customer, Exadata Database Service on Dedicated Infrastructure and Exadata Database Service on Exascale Infrastructure. Clients connect through generated endpoints using Streamable HTTP, while OCI IAM authenticates clients and enforces existing access policies. Customers can choose which resource categories to expose and enable or disable servers.
ArticleSource: Cloudflare
How to test OpenCode session recovery on Cloudflare Durable Objects
Cloudflare’s experimental OpenCodeHarness documents session recovery after eviction, but external tool effects need a separate test. This guide proposes an interruption after a remote commit, then checks stored state, resumed execution, and the destination’s ledger.
ArticleSource: Python Insider
Python 3.15 lazy imports: measure startup costs and test delayed failures
Python 3.15’s explicit lazy imports can defer backend loading until an imported name is first accessed. This proposed AI command-line lab separates startup from first-result latency and tests delayed dependency errors and provider registration.