stac-eo-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STAC_EO_MCP_CATALOG | No | Default STAC catalog to use. Valid values are 'planetary-computer' or 'earth-search'. | planetary-computer |
| STAC_EO_MCP_LOG_LEVEL | No | Logging level. Logs are written to stderr only. | INFO |
| STAC_EO_MCP_MAX_SCENES | No | Maximum number of dates read by the time_series tool. If more are available, they are sampled evenly. | 24 |
| STAC_EO_MCP_OUTPUT_DIR | No | Directory where generated PNG and GeoTIFF files are written. | ~/stac-eo-mcp-output |
| STAC_EO_MCP_MAX_AREA_KM2 | No | Largest bounding box area allowed for pixel reads, in square kilometers. | 100 |
| STAC_EO_MCP_MAX_SEARCH_LIMIT | No | Maximum number of scenes returned by the search_scenes tool. | 50 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_collectionsA | List the collections available in a STAC catalog, with a one-sentence description. |
| search_scenesA | Search scenes intersecting a bbox in a date range, newest first. Returns id, date, cloud cover, a simplified footprint and a preview image link. Cloud cover is for the whole tile, not the bbox. |
| get_scene_detailsB | Key metadata and the list of assets (bands, previews, metadata files) of one scene. |
| compute_indexA | Compute NDVI, NDWI or NBR on one Sentinel-2 L2A scene, reading only the bbox window. |
| time_seriesA | Mean of an index over a bbox for each Sentinel-2 acquisition date in a range. One scene per day, cloudy dates skipped with a reason, sampled evenly when there are more dates than the server limit (default 24). Includes a summary (mean, min/max date, change from first to last). Can take 10-60 s for long ranges. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze_vegetation | Vegetation health of an area over the last months (NDVI time series). |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| indices | Formulas, Sentinel-2 bands, interpretation and the SCL cloud mask. |
| catalogs | Supported STAC catalogs, the default one and the server's request limits. |
TDQS
Scored across 5 tools
Each tool targets a distinct stage of the STAC workflow: catalog browsing, scene search, scene metadata, single-scene index computation, and multi-date time series. The only potential overlap is compute_index vs. time_series, but their scopes (one scene vs. a date range) and descriptions make the boundary clear.
Four of five names follow a clear verb_noun pattern (list_collections, search_scenes, get_scene_details, compute_index). The outlier is time_series, a noun phrase with no verb, but it remains readable and predictable in context.
Five tools are well-scoped for a focused STAC/EO server, covering discovery, retrieval, and two levels of analysis without filler. Each tool earns its place and the surface is neither thin nor bloated.
The core read-only EO workflow is covered: collections, scene search, scene details, and index computation/aggregation. Minor gaps exist, such as no dedicated collection-detail tool, no explicit cloud-cover filter in search_scenes, and no asset download/read tool.