# Earth Snapshot is NASA imagery on demand. AI Agent Connect

> Earth Snapshot connects your AI agent to NASA's Worldview service. It lets your agent render JPEG snapshots of Earth using layers like true color, active fires, aerosols, and land surface data. You can request imagery for specific coordinates or bounding boxes for any date since 2000, all without needing your own API keys.

## Overview
- **Category:** weather-climate
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_D4Tp6lusngTdQyhgv93JDXvAlBapTEgdhYVzEgz7/ai-agent-connect
- **Tags:** satellite-imagery, nasa, worldview, modis, viirs, wildfire, aerosol, remote-sensing, earth-observation, true-color

## Description

You can now give your AI agent eyes on the planet. This MCP pulls directly from NASA's Worldview, allowing your agent to fetch high-resolution satellite imagery for almost any location and time period. Instead of digging through complex geospatial databases, you just tell your agent what you want to see. It can pull up a true color image of a forest, overlay thermal anomaly points to show where fires are burning, or check aerosol levels to track smoke plumes. Because the imagery is delivered as a direct JPEG URL, your agent can instantly present visual evidence of environmental changes. Whether you are looking at vegetation green-up via NDVI or tracking a specific burn scar, the tool handles the heavy lifting of resolving layer IDs and coordinate spans. It even validates dates, so if you ask for imagery from a time before a specific satellite was launched, it tells you rather than giving you a broken image.

## Tools

### find_active_fires
This tool finds thermal anomaly points to show active fires. It renders VIIRS 375 m detections as colored points that you can overlay on true color imagery.

### get_layer_details
This tool retrieves specific metadata for a NASA Worldview layer. It returns the title, instrument used, valid date ranges, and a sample snapshot URL.

### get_earth_snapshot
This tool generates a JPEG URL for a specific satellite layer at a given location. You can provide a lat/lon point or a bounding box to define the view.

### list_imagery_categories
This tool lists the main themes available in the NASA dataset. It covers categories like true color, fires, aerosols, and land surface data.

### list_imagery_layers
This tool provides a list of all available layer IDs within a specific theme. It includes the instrument names and the date ranges each layer covers.

## Prompt Examples

**Prompt:** 
```
Show me a satellite view of the New York area on September 1st, 2026.
```

**Response:** 
```
Here is the MODIS Terra True Color snapshot for New York on September 1st, 2026: https://wvs.earthdata.nasa.gov/api/v1/snapshot?REQUEST=GetSnapshot&LAYERS=MODIS_Terra_CorrectedReflectance_TrueColor&CRS=EPSG%3A4326&TIME=2026-09-01&BBOX=36.70%2C-78.00%2C44.70%2C-70.00&FORMAT=image%2Fjpeg&WIDTH=800&HEIGHT=800
```

**Prompt:** 
```
Were there fires burning in the Amazon on September 15th, 2026?
```

**Response:** 
```
Yes, the VIIRS 375 m thermal anomalies layer shows active fire pixels in the Amazon for that date: https://wvs.earthdata.nasa.gov/api/v1/snapshot?REQUEST=GetSnapshot&LAYERS=VIIRS_SNPP_Thermal_Anomalies_375m_All&CRS=EPSG%3A4326&TIME=2026-09-15&BBOX=-13.00%2C-65.00%2C-3.00%2C-55.00&FORMAT=image%2Fjpeg&WIDTH=800&HEIGHT=800
```

**Prompt:** 
```
How green is the Midwest farm belt right now?
```

**Response:** 
```
The MODIS Terra NDVI layer shows the vegetation levels for the Midwest: https://wvs.earthdata.nasa.gov/api/v1/snapshot?REQUEST=GetSnapshot&LAYERS=MODIS_Terra_NDVI_8Day&CRS=EPSG%3A4326&TIME=2026-09-01&BBOX=35.00%2C-101.00%2C47.00%2C-89.00&FORMAT=image%2Fjpeg&WIDTH=800&HEIGHT=800
```

## Capabilities

### Visualizing Environmental Change
Your agent uses historical layers to compare how a region looked months or years ago.

### Fire Detection
The agent identifies active thermal anomalies using VIIRS data.

### Atmospheric Monitoring
Your agent can pull aerosol and air quality layers to track smoke or dust.

### Vegetation Analysis
The agent accesses NDVI layers to check plant health and green-up patterns.

### Layer Composition
Your agent can stack fire or aerosol detections on top of true color images.

## Use Cases

### Wildfire Tracking
An agent can overlay thermal anomaly points on a true color map to show exactly where a fire is burning.

### Smoke Plume Mapping
You can track the movement of aerosols across continents by requesting specific atmospheric layers.

### Crop Health Monitoring
Use NDVI layers to see the difference between harvested fields and dense forest canopy.

### Historical Comparison
Compare a current landscape to a snapshot from years ago to see the impact of land use changes.

## Benefits

- No NASA API keys or credentials required to run requests.
- Direct JPEG URLs allow for instant viewing in any chat interface.
- Access to data spanning back to the year 2000.
- Automated date validation prevents empty or broken image renders.

## How It Works

Connecting to Earth Snapshot is a one-time setup that gives your agent immediate access to NASA's data.

1. Connect the Earth Snapshot MCP to your AI client via Vinkius.
2. Ask your agent for a specific visual, like a satellite view of a city.
3. The agent identifies the correct NASA layer and coordinates.
4. The MCP generates a permanent JPEG URL for that specific view.
5. The image appears directly in your chat interface.

## Frequently Asked Questions

**Do I need a NASA account to use this?**
No. This MCP handles the connection to NASA Worldview, so you don't need to manage any API keys or credentials.

**Can I see images from many years ago?**
Yes. Most layers in this MCP go back as far as the year 2000.

**What happens if I ask for a date when no satellite was active?**
The tool checks the published date range for every layer. If the date is out of range, it will refuse the request rather than returning a blank image.

**Can I overlay different types of data?**
Yes. You can stack layers, such as putting fire detections or aerosol data on top of a true color image.

**Which AI clients can use this MCP?**
You can use this with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

**Do I need an API key?**
No. This reads NASA's public Worldview services — the layer catalog and the snapshot renderer — which require no key or account.

**Does the tool return the image itself?**
It returns a URL that renders the image on request. The URL is stable and never expires — open it in a browser, embed it, or fetch it. Worldview composes the JPEG from the layer and region at request time, so it works for any date the layer covers and any size up to 2000 px.

**Why was my date rejected?**
Layers have published lifetimes, and a date outside that range renders a blank image instead of returning an error — so the tool checks and refuses. Night lights only covers 2012 and 2016, snow extent ended in 2024, and nothing can be rendered for a future date. Call get_layer_details to see a layer's range, or list_imagery_layers for alternatives in the same theme.

**What does it mean when a fire detection frame looks empty?**
The VIIRS 375 m layer colours hot pixels over a black background, so a frame with no coloured points means no thermal anomalies were recorded in that region that day — that is the answer, not a failed render. Compare it with the composite, which draws the same detections on true-colour imagery, or widen the region.