satellite-imagery-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for the hosted Streamable HTTP mode (default 3000). | 3000 |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| find_imageryA | Finds satellite scenes of an area (bbox or lat/lon) between two dates: Sentinel-2, Landsat, Sentinel-1 radar or NAIP. Ranks by how much of the area each scene covers, cloud cover and date, and returns preview, true-colour image and STAC item links with the data licence. |
| scene_assetsA | Lists the bands and files of one scene found with find_imagery: key, title, common band name, resolution, media type and download URL, with the scene's date, cloud cover, projection and footprint bbox. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: find_imagery searches and ranks scenes, while scene_assets retrieves file-level details for a specific scene. There is no overlap or ambiguity between them.
Both tool names follow a consistent verb_noun pattern (find_imagery, scene_assets), though scene_assets uses a noun-first structure rather than a verb. The pattern is still predictable and readable.
With only two tools, the server feels minimal but coherent: one for discovery and one for asset access. It is borderline because a satellite imagery workflow might expect additional operations like downloading or processing, but the two tools cover the core search-to-assets flow.
The server covers the essential discovery-to-asset pipeline, but lacks operations like direct download, scene metadata browsing, or comparison of multiple scenes. Agents can work around this by using the provided URLs, but the surface is thin for a full satellite imagery workflow.