Drive browser automation toward a specified goal with an agent that chooses each step, accepts context variables, and verifies completion via a visible selector, returning the outcome and cost.
Submit multiple queries for asynchronous batch processing with approximately 50% cost discount. Queries run within 24 hours; results are retrieved after completion.
List all layers in a spatial data source (FileGDB, GeoPackage, Shapefile, GeoJSON, KML, etc.) with names and geometry types. Safe for large catalogs and lock files, preventing OpenFileGDB hangs.
An MCP server providing geospatial analysis tools for raster and vector data, integrated with a reflection system that requires AI agents to justify their methodological decisions. It enables accurate mapping and spatial operations by ensuring reasoned choices for coordinate systems, resampling, and data transformations.
Provides persistent goal-tracking with external evaluation for agentic CLIs, enabling run-until-done loops where an agent works across turns until a condition is met.
Submit a single independent question to Gemini without maintaining session history. Suitable for one-off lookups or batch queries where context is unnecessary.
Analyze a codebase by asking questions. Gemini autonomously reads files, lists directories, and searches code to provide answers, eliminating the need to pre-read files.
Create calendar events by typing plain-language descriptions—Google's NLP parser converts phrases like "Lunch with Sarah tomorrow at noon" into scheduled events on your chosen calendar.