GeoSight MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GeoSight MCP Serverdetect deforestation in the Amazon rainforest over the past year"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
๐ฐ๏ธ GeoSight MCP Server
Production-ready Satellite Imagery Analysis MCP Server - Analyze Earth observation data through natural language queries.
"Show me deforestation in the Amazon over the last year"
"Detect flooding in Bangladesh from satellite imagery"
"Track urban expansion around Mumbai since 2020"
๐ Features
Feature | Description |
Land Cover Classification | Identify forests, water, urban areas, agriculture |
Vegetation Analysis (NDVI) | Monitor crop health, deforestation, drought |
Water Detection (NDWI) | Track floods, reservoirs, coastal changes |
Change Detection | Compare imagery across time periods |
Object Detection | Find ships, planes, buildings, solar farms |
Automated Reports | Generate PDF/HTML reports with maps |
Related MCP server: Google Earth Engine MCP Server
๐๏ธ Architecture
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ CLIENT LAYER โ
โ Claude Desktop / Streamlit Dashboard / API โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ MCP Protocol (stdio/SSE)
โโโโโโโโโโโโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ MCP SERVER (FastAPI) โ
โ โโโโโโโโโโโโ โโโโโโโโโโโโ โโโโโโโโโโโโ โ
โ โ Tools โ โ Auth โ โ Queue โ โ
โ โ Router โ โ Layer โ โ (Celery) โ โ
โ โโโโโโโโโโโโ โโโโโโโโโโโโ โโโโโโโโโโโโ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ PROCESSING ENGINE โ
โ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโ โ
โ โ Imagery โ โ ML Models โ โ Visualize โ โ
โ โ Fetcher โ โ Pipeline โ โ Engine โ โ
โ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ DATA LAYER โ
โ โโโโโโโโโโโโ โโโโโโโโโโโโ โโโโโโโโโโโโ โ
โ โ Postgres โ โ Redis โ โ MinIO โ โ
โ โ +PostGIS โ โ Cache โ โ Storage โ โ
โ โโโโโโโโโโโโ โโโโโโโโโโโโ โโโโโโโโโโโโ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ๐ Quick Start
Prerequisites
Python 3.11+
Docker & Docker Compose
Sentinel Hub Account (free tier available)
1. Clone & Setup
git clone https://github.com/yourusername/geosight-mcp.git
cd geosight-mcp
# Create virtual environment
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# Install dependencies
pip install -e ".[dev]"2. Configure Environment
cp .env.example .env
# Edit .env with your API keys3. Start Services
# Development mode
docker-compose up -d redis postgres minio
# Run MCP server
python -m geosight.server
# Or run everything with Docker
docker-compose up -d4. Connect to Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"geosight": {
"command": "python",
"args": ["-m", "geosight.server"],
"cwd": "/path/to/geosight-mcp",
"env": {
"SENTINEL_HUB_CLIENT_ID": "your-client-id",
"SENTINEL_HUB_CLIENT_SECRET": "your-client-secret"
}
}
}
}๐ง Available MCP Tools
search_imagery
Find available satellite imagery for a location and date range.
# Example usage through Claude
"Find Sentinel-2 imagery for New Delhi from last month"calculate_ndvi
Calculate vegetation index to assess plant health.
# Returns: NDVI map + statistics
"Calculate NDVI for agricultural region near Punjab"calculate_ndwi
Calculate water index to detect water bodies and flooding.
# Returns: Water mask + area calculations
"Show water bodies in Kerala during monsoon season"detect_land_cover
Classify land into categories: forest, water, urban, agriculture, barren.
# Returns: Classification map + percentages
"Classify land cover for Bangalore metropolitan area"detect_changes
Compare two time periods and highlight differences.
# Returns: Change map + statistics
"Show construction changes in Dubai between 2020 and 2024"detect_objects
Find specific objects in imagery (ships, planes, buildings).
# Returns: Detected objects with bounding boxes
"Detect ships in Mumbai harbor"generate_report
Create comprehensive PDF/HTML report with analysis.
# Returns: Downloadable report
"Generate environmental report for Amazon rainforest region"๐ Data Sources
Source | Type | Resolution | Frequency | Cost |
Sentinel-2 | Optical (13 bands) | 10m | 5 days | Free |
Sentinel-1 | SAR (radar) | 10m | 6 days | Free |
Landsat 8/9 | Optical + Thermal | 30m | 16 days | Free |
MODIS | Global coverage | 250m-1km | Daily | Free |
๐ง ML Models
Pre-trained Models Included
Land Cover Classifier - EuroSAT-based CNN (ResNet50)
Change Detection - Siamese U-Net architecture
Object Detection - YOLOv8 trained on DOTA dataset
Segmentation - DeepLabV3+ for semantic segmentation
Model Performance
Model | Task | Accuracy | Inference Time |
Land Cover | Classification | 94.2% | ~200ms |
Change Detection | Binary change | 91.8% | ~500ms |
Object Detection | Ships/Planes | 87.5% mAP | ~300ms |
๐ณ Deployment
Docker Deployment
# Build and run all services
docker-compose -f docker-compose.prod.yml up -d
# Check logs
docker-compose logs -f geosight-mcpCloud Deployment (Railway/Fly.io)
# Railway
railway up
# Fly.io
fly launch
fly deployKubernetes
kubectl apply -f k8s/๐ Project Structure
geosight-mcp/
โโโ src/
โ โโโ geosight/
โ โโโ __init__.py
โ โโโ server.py # MCP server entry point
โ โโโ tools/ # MCP tool implementations
โ โ โโโ __init__.py
โ โ โโโ imagery.py # Image search & fetch
โ โ โโโ indices.py # NDVI, NDWI calculations
โ โ โโโ classification.py # Land cover classification
โ โ โโโ change_detection.py
โ โ โโโ object_detection.py
โ โ โโโ reports.py # Report generation
โ โโโ models/ # ML models
โ โ โโโ __init__.py
โ โ โโโ land_cover.py
โ โ โโโ change_detector.py
โ โ โโโ object_detector.py
โ โโโ services/ # External service integrations
โ โ โโโ __init__.py
โ โ โโโ sentinel_hub.py
โ โ โโโ earth_engine.py
โ โ โโโ storage.py
โ โโโ utils/ # Utilities
โ โโโ __init__.py
โ โโโ geo.py # Geospatial utilities
โ โโโ visualization.py
โ โโโ cache.py
โโโ tests/
โโโ config/
โโโ scripts/
โโโ dashboard/ # Streamlit dashboard
โโโ docs/
โโโ docker-compose.yml
โโโ Dockerfile
โโโ pyproject.toml
โโโ README.md๐งช Testing
# Run all tests
pytest
# With coverage
pytest --cov=geosight --cov-report=html
# Integration tests
pytest tests/integration/ -v๐ Monitoring
Prometheus metrics at
/metricsHealth check at
/healthGrafana dashboards included in
config/grafana/
๐ค Contributing
Fork the repository
Create feature branch (
git checkout -b feature/amazing-feature)Commit changes (
git commit -m 'Add amazing feature')Push to branch (
git push origin feature/amazing-feature)Open a Pull Request
๐ License
MIT License - see LICENSE for details.
๐ Acknowledgments
Sentinel Hub for satellite data access
EuroSAT for land cover dataset
DOTA for object detection dataset
๐ฌ Contact
Your Name - @yourtwitter
Project Link: https://github.com/yourusername/geosight-mcp
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- -license-quality-maintenanceEnables satellite imagery analysis through Google Earth Engine, allowing users to search datasets, calculate vegetation indices like NDVI, filter collections by location and date, and export imagery to cloud storage. Supports major satellite datasets including Sentinel-2, Landsat, and MODIS for applications like agriculture monitoring and deforestation tracking.Last updated
- Alicense-qualityDmaintenanceMCP server for interacting with Google Earth Engine, enabling geospatial analysis such as dataset visualization, statistics computation, and search via AI assistants.Last updated13MIT
- AlicenseAqualityCmaintenanceA Python MCP server that provides unified access to satellite and geospatial data through natural language queries, with automatic place name geocoding and support for raster, vector, and Zarr formats.Last updated24Apache 2.0
- Alicense-qualityDmaintenanceEnables AI agents to search, compare pricing, and order satellite imagery from 150+ satellites across 12+ providers via natural language.Last updatedMIT
Related MCP Connectors
MCP server for Mireye Earth โ federal-source-cited geospatial data for any MCP-aware agent.
GibsonAI MCP server: manage your databases with natural language
Geospatial MCP server for earthquake, tsunami, volcano, disaster, and FX data queries.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/armaasinghn/geosight-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server