Skip to main content
Glama

groundstation

Earth data, agent ready. A Development Seed MCP prototype giving easy access to a variety of cloud-native geospatial stacks, with visual examples and repeatable workflows called "field tests".

Cloud-native geospatial exists because the satellite archives grew to petabytes, and downloading whole scenes to look at one field stopped making sense. With STAC to find the data, cloud-optimized formats (COG, Zarr) to read only the pixels you need, and TiTiler to render them on demand, most questions about a place can be answered in seconds against the open archive. That is the exciting part: an agent can now reach the whole Earth record as easily as it reaches a web page.

Ask a question about any place on Earth. groundstation finds satellite imagery, active fires, disaster alerts and weather, does the pixel math, and returns data, stories and interactive maps. 3 ways in:

flowchart LR
    A["🗣 AI Agent (Claude, GPT, Gemini, local) <br/>(MCP server + skill)"] --> T
    B["🖥 Web"] --> T
    C["⏰ Scheduled briefings"] --> T
    T["groundstation tools"] --> D["STAC catalogs<br/>Earth Search · NASA VEDA<br/>Planetary Computer · UK EO DataHub"]
    T --> E["TiTiler<br/>tiles · previews · band math"]
    T --> F["EONET · GDACS · Open-Meteo<br/>events & weather"]
    T --> G["🗺 shareable map artifacts<br/>📄 draft briefs"]

Everything runs against public, keyless endpoints, so it works anywhere with nothing to sign up for. It supports any MCP client, like Claude Code, Codex, Gemini CLI or Cursor.

What it lets an agent do

  • Answer a question about a place. Find the right scene, do the pixel math, and come back with numbers, their caveats, and a map to share

  • Think alongside you. In a brainstorm or design session, pull real imagery and numbers for a place while the idea is still forming, and sketch a map the room can react to

  • Explore before committing. See what data exists for a place, at what resolution and how fresh, before anyone scopes a project around it

  • Watch places and report back. Brief you each morning on what changed, and stay quiet about what didn't

Related MCP server: Gods Eye Geospatial MCP

Examples

5 real asks, run on real data. Each links its map; the full write-up is real-world-asks.

"Mt St Helens eruption 1980" The tools found 2 Landsat MSS scenes from the same orbit, 1979-09-12 and 1980-09-15, both 0.0% cloud. Over the box around the mountain the median vegetation index fell from 0.2691 to -0.0043. A swipe map puts the 2 scenes side by side. Map

"Hurricane Patricia 2015" Landsat 8 has the coast on 2015-10-13 and 2015-11-30, and the median vegetation index over a box on the land went from 0.8712 to 0.8226. The after scene is cloudier, so that number is a hint, not a damage measure. Map

"Switzerland's glaciers are disappearing at an alarming rate, losing more than 5% of their ice volume in 2026 alone" Sentinel-2 has the Great Aletsch glacier on 2017-08-23 and 2026-08-30, and the late-summer snow and ice index rose 7.9%. That is snow on the day, not ice volume, so the 5% volume loss stays with the glacier monitoring network's measurement. The tools showed the glacier on both dates with a swipe map. Map

"Eagle Creek fire 2017, Columbia River Gorge" Sentinel-2 has the gorge on 2017-08-26, 7 days before the fire started on 2017-09-02 (a date from outside the tool output), and on 2017-10-05, both under 0.4% cloud and from the same tile. Over the box the mean burn index (NBR) fell from 0.6415 to 0.4305, -32.9%, and the swipe map shows the burn south of the river. Map

"What's going on around Portland, Oregon right now: fires, floods, weather, and when the next clear satellite pass is" At 04:59 UTC on 2026-10-27, GDACS listed 0 active events but EONET returned a server error, so that is not an all-clear. It rained 15.1 mm on 2026-10-25 with more forecast, the next daylight pass is Sentinel-3B at 18:16 UTC on 2026-10-27, with Landsat 8 at 18:56 (passes are predicted, not cloud), and the clearest Sentinel-2 scene from 2026-10-12 to 2026-10-26 is 2026-10-15 at 0.3% cloud. Map

Quickstart

You need uv. Clone the repo and build the environment:

git clone https://github.com/dannybauman/groundstation && cd groundstation && uv sync

Then point any MCP client at it (Claude, Codex, Gemini CLI, Cursor, a local model's client). Most read a config like this:

{
  "mcpServers": {
    "groundstation": {
      "command": "uv",
      "args": ["--directory", "/path/to/groundstation", "run", "groundstation"]
    }
  }
}

The skills in skills/ are plain markdown, so any agent can read them as instructions. Then ask for a map of your hometown.

In Claude Code, the plugin brings the server and the skills in one step, with no clone:

/plugin marketplace add dannybauman/groundstation
/plugin install groundstation@groundstation

The first launch builds the server's environment, so the tools appear a few seconds after the agent starts. With the plugin you can also just ask: "demo groundstation", "is groundstation running", "open the field tests" and "brief me on Lisbon" all run through the groundstation skill.

If the tools don't show up, run the preflight. It walks the setup chain in the order it breaks (uv, server env, Claude Code CLI, plugin wiring, endpoints) and prints the fix for the first broken link:

bash scripts/doctor.sh

Without an agent:

# the web console, at http://127.0.0.1:8765
uv run --group web groundstation-web

# a brief for one place, or the morning sweep over a watch list
uv run briefing/brief.py --place "Chelan County, Washington" --days 10
uv run briefing/brief.py --fleet briefing/fleet.json

Updating

With a clone, git pull and restart your agent. Claude Code plugin installs are cached per version, so they stay as they were until you update them:

claude plugin marketplace update groundstation
claude plugin update groundstation@groundstation

Then restart Claude Code. scripts/doctor.sh says which copy you are running and whether it is behind.

Things to ask it

Paste any of these into your agent as is.

Find the clearest Sentinel-2 scene of Lake Chelan from the past 2 weeks, tell me what's burning nearby, and give me a map I can share.
How much surface water is on the Barotse Floodplain right now vs early March? Use NDWI, give me numbers and a swipe map.
What does NASA VEDA have on the Caldor fire? Put the burn severity layer over a current scene.
Any active flood alerts along the Rio Grande between El Paso and Laredo? Alerts, week-ahead rain, latest usable imagery, one map.
Give me a 3D fly-through of Torres del Paine.
Make me a postcard of that I could post.

The first search_datasets call takes a few seconds while collection lists cache. After that it is near instant for an hour.

What an agent gets

Tool

What it does

Backed by

geocode

place name to coordinates and a bbox

the fuzzy index in Gazet, Development Seed's geocoder (Overture divisions, urban centres, Natural Earth), with Nominatim as the fallback

list_catalogs / search_datasets / describe_collection

find the right data across catalogs, filtered by place and resolution (bbox/place, max_gsd)

Earth Search, NASA VEDA, Planetary Computer, UK EO DataHub (open data), plus a curated zarr list (HRRR forecast, ERA5, GFS and MUR SST as metadata)

search_imagery

recent scenes with cloud filtering, plus the scene to start from and why

STAC APIs, or a stac-geoparquet archive via rustac (offline)

write_archive

cache a live search as a stac-geoparquet file that search_imagery takes as its catalog

rustac

preview_item / tile_url_template

browser-openable previews and XYZ tiles

titiler.xyz, VEDA raster API, PC data API

compute_statistics

band math over a scene: NDVI is (nir-red)/(nir+red). With catalog="zarr", a clipped statistic from a Zarr forecast (HRRR, CONUS only), e.g. the temperature over Laredo tomorrow

TiTiler statistics; xarray + zarr + obstore

compare_dates

"what changed?" in one call: same-tile scenes, index delta, swipe map

all of the above

render_map

self-contained interactive HTML maps. 2 rasters become a swipe compare

MapLibre + live tiles

render_map_3d

terrain fly-throughs: imagery draped over real relief

MapLibre terrain + keyless AWS Terrarium tiles

render_timelapse

2 to 12 frames (default cap 8) of one place over time, with prev / play / next; a frame loads tiles only when shown

MapLibre, hidden layers fetch nothing

render_postcard

share cards with the pixels embedded and attribution baked in, so nothing expires

TiTiler previews

active_events / weather_summary

open fires, floods and storms, plus the past and coming week of weather

NASA EONET, GDACS, Open-Meteo

smoke_forecast

near-surface smoke now and hours ahead (CONUS)

NOAA HRRR smoke through raster.eoapi.dev, model guidance not observation

next_pass

when a satellite could next image a place

Celestrak orbits, constellations read from eo-predictor's catalog

conditions_brief

current conditions around a place in one call: dryness, wind, events, the latest look, the next pass

the tools above

Numbers come with caveats. If a change figure sits on a cloudy scene, or a statistic covers a whole tile, or the tiler could not read a scene, the tool says so next to the number. Details in docs/adr-caveats.md.

Every map and postcard has a Stack panel, and a brief has it on its map, not on the page. It lists what made it, in order. docs/stack.md is the list, and a new tool is one line.

The skills in skills/ tell the agent which catalog to use, how assets are named, how to compute the common indexes, and to end every spatial answer with a map.

Briefings

A briefing runs on a schedule and says what changed at a place: new scenes, events, weather, NDVI against last month, a CALM, WATCH or ACT level, and what to look at next. It is an HTML page you can share. Each place remembers its last run, so "what changed" means since then. The written summary comes from claude -p by default, or a local model if you set one up. Without either, you get a data-only brief.

Scheduling, Slack delivery and local-model summaries are in docs/briefing.md.

titiler.xyz is shared

Tiles, previews and pixel math use titiler.xyz by default. Development Seed runs it as a free demo, and it rate-limits (HTTP 429) when busy. For scheduled briefings, batch runs or a live demo, run your own:

docker compose up -d titiler                          # TiTiler is one container, see compose.yml
export GROUNDSTATION_TITILER=http://localhost:8000    # everything routes there

Any TiTiler with the /stac router works. One catch: NAIP and Landsat on Earth Search are requester-pays. titiler.xyz has credentials for those. A local TiTiler returns 500s on them until you add your own (see compose.yml) or use Planetary Computer's copies.

Checks

  • uv run evals/unit_checks.py: offline, runs in CI on pushes to main and on pull requests

  • uv run evals/run_evals.py: live, against the real endpoints, on demand and weekly in CI

  • uv run evals/brief_checks.py: every event a brief mentions has to be in its input data

More

  • docs/samples/: four field tests to browse: showcase-every-tool, real-world-asks, tour-five-flows, land-classification. Your own field tests are gitignored

  • docs/architecture.md: how it fits together and what is left out on purpose

  • docs/plan-2026-10-devseed-stack.md: the plan, most of it shipped (the smoke forecast, Zarr stores, cross-catalog search, stac-geoparquet archives); the open items are at the end

  • For deeper exploration, stac-map renders COGs in the browser with deck.gl-raster. Tiles and pixel math use TiTiler

MIT licensed, see LICENSE.

Available Tools

12 tools
active_eventsA

Current natural events and disaster alerts, optionally filtered to a bbox.

Combines NASA EONET (wildfires, storms, volcanoes, floods...) and GDACS global disaster alerts. bbox is [w, s, e, n]. Returns compact event lists with coordinates suitable for mapping.

Inputs: bbox, days. Returns: object

compare_datesA

Compare two time windows over a place: matched scenes, index delta, swipe map.

The most common Earth question is "what changed?" — this answers it in one call. Windows are RFC3339 ranges ("2026-06-01T00:00:00Z/2026-06-30T23:59:59Z"); window_after defaults to the last 14 days, window_before to roughly one month earlier. Picks Sentinel-2 scenes from the SAME MGRS tile (best AOI coverage, lowest cloud), computes the expression's stats for both dates, and writes a side-by-side swipe map. Returns scenes, means, delta, and map_path.

Inputs: bbox, label, place, expression, +3 more. Returns: object

compute_statisticsB

Compute pixel statistics (min/max/mean/std/histogram) for a STAC item.

expression is band math over asset names, e.g. "(nir-red)/(nir+red)" for NDVI on Sentinel-2 (Earth Search asset names). Optionally clip to an AOI GeoJSON Feature. Backed by TiTiler /stac/statistics.

Inputs: catalog (required), item_id (required), collection_id (required), assets, +2 more. Returns: object

describe_collectionB

Get a collection's description, extent, and asset/band layout.

Inputs: catalog (required), collection_id (required). Returns: object

geocodeA

Resolve a place name to coordinates and a bounding box.

Tries Development Seed's Gazet small-model geocoder first, then falls back to OSM Nominatim. Use concise names ("Barotse Floodplain", "Chelan County") rather than long phrases. Returns {name, lat, lon, bbox: [w, s, e, n], source}.

Inputs: query (required). Returns: object

list_catalogsA

List the STAC catalogs this server can search, with what each is good for.

Inputs: no named parameters. Returns: result

preview_itemA

Get a browser-openable PNG preview URL for a STAC item.

Routes to the right raster backend per catalog: titiler.xyz for Earth Search, NASA VEDA's raster API, or Planetary Computer's signing data API. Optional rescale like "0,3000" for non-visual assets.

Inputs: catalog (required), item_id (required), collection_id (required), assets, +2 more. Returns: object

render_mapA

Write a self-contained interactive HTML map and return its file path.

layers is a list of: {"type": "item", "name": ..., "catalog": ..., "collection_id": ..., "item_id": ..., "assets": [...], "rescale": "0,3000", "colormap_name": ..., "expression": "(nir-red)/(nir+red)"} # expression for index layers {"type": "raster", "name": ..., "tiles": "https://..{z}/{x}/{y}.."} {"type": "geojson", "name": ..., "data": , "color": "#hex"} Item layers resolve to the right tiling backend automatically. The HTML is shareable: MapLibre + live tile URLs, no server of ours required.

compare: True renders two raster layers as a draggable swipe (before/after), False stacks them as toggleable overlays. Default None auto-decides: swipe only when both rasters come from the SAME collection (a comparison), overlay when they differ (e.g. burn severity over imagery — pass opacity ~0.75).

Inputs: bbox (required), title (required), layers (required), compare, +2 more. Returns: object

search_datasetsA

Find dataset collections matching keywords, across all catalogs or one.

Case-insensitive match against collection id, title, description, and keywords. Returns up to 20 hits with {catalog, id, title, summary}.

Inputs: keywords (required), catalog. Returns: result

search_imageryA

Search a STAC catalog for imagery/data items.

Provide either bbox [w, s, e, n] or a place name (geocoded for you). datetime_range is RFC3339, e.g. "2026-06-01T00:00:00Z/2026-07-09T00:00:00Z". Returns compact items sorted newest first; feed self_url/ids into preview_item, compute_statistics, or render_map.

Inputs: catalog (required), collections (required), bbox, limit, +3 more. Returns: object

tile_url_templateB

XYZ tile URL template ({z}/{x}/{y}) for a STAC item, for web maps.

For index layers (NDVI etc.) pass expression over asset names, e.g. "(nir-red)/(nir+red)" with rescale="-1,1" and colormap_name="rdylgn" — supported on earth-search; ignored for veda/planetary-computer.

Inputs: catalog (required), item_id (required), collection_id (required), assets, +3 more. Returns: result

weather_summaryA

Recent and forecast weather for a point (Open-Meteo, no key needed).

Returns daily max/min temperature, precipitation, max wind speed, and dominant wind direction (degrees, meteorological: 0=N, 90=E — the direction wind comes FROM) for past_days back and 7 days ahead. Wind direction matters for smoke, ash, and plume dispersal questions.

Inputs: lat (required), lon (required), past_days. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 12 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: events, change detection, statistics, catalog metadata, geocoding, preview, map rendering, dataset search, imagery search, tile URL generation, and weather. No two tools appear to do the same thing, and descriptions clarify boundaries.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with lowercase and underscores (e.g., active_events, compare_dates, search_imagery). No mixing of conventions.

    Tool Count5/5

    12 tools is well-scoped for the Earth observation domain: covering discovery, search, analysis, visualization, and weather. Each tool earns its place without redundancy or overwhelming number.

    Completeness5/5

    The tool set covers the full lifecycle for the intended use: finding data (search_datasets, search_imagery, list_catalogs), accessing metadata (describe_collection), analyzing (compute_statistics, compare_dates), visualizing (preview_item, render_map, tile_url_template), and integrating external data (active_events, weather_summary, geocode). No obvious gaps.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers