The Earth Engine Visualization Toolkit for Python

Docs Google Earth Engine

geeViz makes exploring, visualizing, and analyzing Earth Engine data and geospatial imagery easy in Python. Whether you’re an analyst, scientist, or just getting started, geeViz offers interactive mapping, time series, and advanced charting—without the JavaScript overhead.

Developed by RedCastle Resources, geeViz features a powerful, customizable map viewer and Pythonic interfaces for working with Google Earth Engine (GEE).

• Interactive Map Viewer (launches in your browser)
• Layer toggling, opacity, visualization tools, querying, & area charting
• Dynamic time-lapse creation from GEE ImageCollections
• Built-in charting & analysis tools (point/polygon, time series, area stats)
• Inline zonal summary & charting (geeViz.outputLib.charts, formerly geeViz.chartingLib) — run zonal stats and produce Plotly charts (time series, bar, grouped bar, donut, scatter, per-feature time series subplots, Sankey) directly in notebooks
• Summary area retrieval (geeViz.getSummaryAreasLib) — 15 functions returning filtered ee.FeatureCollection objects for political boundaries, USFS units, census geographies, buildings, roads, and protected areas
• Jupyter/Colab support and standalone scripting
• Supports Landsat, Sentinel-2, MODIS, LCMS, LCMAP, and more
• Extensive examples and ready-to-run wrappers
• Built-in MCP server for AI coding assistants (Cursor, Claude Code, VS Code Github Copilot, Windsurf, AntiGravity, etc...)

• PyPI: pypi.org/project/geeViz
• Docs/Home: geeviz.org
• Notebooks & Scripts: examples/
• Community Repo: github.com/gee-community/geeViz
• Forest Service GitHub: code.fs.usda.gov/forest-service/geeViz

• geeViz Documentation and API Reference
• See examples/ for Jupyter/Colab notebooks and scripts.
• Need help? Email us at info@geeviz.org.

The fastest way to get started:

1. Sign up for Google Earth Engine
2. Install geeViz via pip:

   pip install geeViz

3. Authenticate your Google account with Earth Engine:

   earthengine authenticate

Some geeViz features (googleMapsLib, outputLib.reports LLM narratives) require API keys from Google Cloud. These are optional — core GEE functionality works without them.

Gemini API Key (for AI-generated report narratives and image interpretation):

1. Go to Google AI Studio
2. Click Create API Key → select a project → copy the key

Google Maps Platform API Key (for geocoding, Street View, places, elevation, air quality, solar):

1. Go to Google Cloud Console → select/create a project
2. Navigate to APIs & Services → Credentials → Create Credentials → API Key
3. (Recommended) Restrict the key to: Geocoding, Street View Static, Places (New), Elevation, Air Quality, Solar, Roads, Maps Static

Store your keys in a .env file in your geeViz package directory (alongside geeView.py):

# .env file in your geeViz package directory
GEMINI_API_KEY=your_gemini_api_key_here
GOOGLE_MAPS_PLATFORM_API_KEY=your_maps_platform_key_here

You can also set these as environment variables. The .env file is loaded automatically by googleMapsLib and outputLib.reports on import.

Optional pip extras:

pip install geeViz[gemini]         # Adds google-genai for AI features
pip install geeViz[segmentation]   # Adds torch + transformers for SegFormer
pip install geeViz[all]            # Everything

geeViz includes a built-in MCP (Model Context Protocol) server with 22 tools that give AI coding assistants live access to geeViz and Google Earth Engine. Instead of generating code from training data (which is often wrong or outdated), your AI assistant can look up real function signatures, read actual example scripts, execute and test code, inspect assets, export data, manage tasks, and more.

Works with Cursor, Claude Code, VS Code with GitHub Copilot, Windsurf, and any MCP-compatible client. The mcp SDK is included as a dependency — no extra install needed.

1. Add a config file for your editor (see MCP Server docs):

   {
     "mcpServers": {
       "geeviz": {
         "command": "python",
         "args": ["-m", "geeViz.mcp.server"]
       }
     }
   }

2. Copy the agent instructions from geeViz/mcp/agent-instructions.md into your editor's instructions file (.github/copilot-instructions.md, .cursorrules, CLAUDE.md, or .windsurfrules).

The 22 tools are organized into categories:

Charting (cl.summarize_and_chart()), thumbnails (tl.generate_thumbs()), EDW queries (edwLib), and geocoding (gm.geocode()) are accessed via run_code for maximum flexibility.

For the complete tool reference, architecture details, and usage examples, see the MCP Server README and the online MCP Server guide.

geeViz comes with ready-to-run examples and templates for fast onboarding.

from geeViz.examples import geeViewExample

from geeViz.examples import timeLapseExample
from geeViz.examples import getLandsatWrapper
from geeViz.examples import getSentinel2Wrapper
from geeViz.examples import getCombinedLandsatSentinel2Wrapper
from geeViz.examples import harmonicRegressionWrapper
from geeViz.examples import LANDTRENDRWrapper
from geeViz.examples import LANDTRENDRViz
from geeViz.examples import CCDCViz
from geeViz.examples import lcmsViewerExample
from geeViz.examples import LCMAP_and_LCMS_Viewer
from geeViz.examples import phEEnoVizWrapper
from geeViz.examples import GFSTimeLapse

• Interactive notebooks are in the examples/ directory (see docs ➔).
• The geeViz map viewer also works directly inside Jupyter and Google Colab.

• One line mapping: Map any GEE image or collection instantly
• Interactive: Toggle layers, set opacity, area/point query, and chart
• Dynamic Time-Lapses: Animate temporal stacks and export GIFs
• No JavaScript required: Pure Python interface

We love contributions and new users!

• Share a GEE script, notebook, or suggestion?
  info@geeviz.org
• Pull requests & feature requests:
  github.com/gee-community/geeViz

geeViz is released under the Apache 2.0 License.
See the LICENSE file for details.