An astronaut overseeing a futuristic data hub

Connect Earth Snapshot to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get real satellite snapshots for any place and any date.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 5 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 5 available through NASA Worldview.

  1. 01

    Get earth snapshot

    This capability 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.

  2. 02

    Find active fires

    This capability 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.

  3. 03

    Get layer details

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

Capability set02 / 02

04-05

2 capabilities in this set.

Part of 5 available through NASA Worldview.

  1. 04

    List imagery categories

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

  2. 05

    List imagery layers

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

Real work

What teams actually run

01

Wildfire Tracking

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

02

Smoke Plume Mapping

You can track the movement of aerosols across continents by requesting specific atmospheric layers.

03

Crop Health Monitoring

Use NDVI layers to see the difference between harvested fields and dense forest canopy.

04

Historical Comparison

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

One connector, every AI

NASA Worldview works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put NASA Worldview to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

900ms average. Fast in production.

NASA Worldview is checked daily against the live service.

Daily averagePeak 997ms
Oct 3Today
Fastest day
755ms
Slowest day
997ms
14-day trend
Stable-2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 5 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of NASA Worldview, so you can see the experience inside your AI.

It does not authenticate your account with NASA Worldview. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

NASA Worldview Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_D4Tp6lusngTdQyhgv93JDXvAlBapTEgdhYVzEgz7/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — NASA Worldview capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "earth-snapshot-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_D4Tp6lusngTdQyhgv93JDXvAlBapTEgdhYVzEgz7/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up NASA Worldview in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work NASA Worldview owners hand off.

This MCP is built for professionals who need to verify ground truths using satellite data without writing custom code.

  • 01

    Environmental Researchers

    They hand off the task of finding specific historical satellite layers to the agent.

  • 02

    Disaster Response Analysts

    They use the agent to quickly get visual snapshots of active fire zones or smoke plumes.

  • 03

    Agricultural Analysts

    They ask the agent to monitor vegetation health and soil conditions via NDVI.

FAQ

Questions NASA Worldview owners ask.

  • 01

    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.

  • 02

    Can I see images from many years ago?

    Yes. Most layers in this MCP go back as far as the year 2000.

  • 03

    What happens if I ask for a date when no satellite was active?

    The capability 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.

  • 04

    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.

  • 05

    Which AI clients can use this MCP?

    You can use this with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 06

    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.

  • 07

    Does the capability 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.

  • 08

    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 capability 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.

  • 09

    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.

Connect NASA Worldview to Claude, Cursor, ChatGPT & more