Skip to main content
Glama
loosephoto

space-finder-mcp

by loosephoto
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

stac_search

Search satellite data (Sentinel-2, Landsat, NAIP, DEM) by location, date, and cloud cover via AWS Earth Search. No authentication needed.

Instructions

AWS Earth Search で衛星データ（Sentinel-2 / Landsat / NAIP / DEM）をSTAC検索する（認証不要）。

例:「東京のLandsat画像」「関東のSentinel-2の雲が少ない画像」
場所は bbox（"lon_min,lat_min,lon_max,lat_max"）または place（地名）。
content に表示用サマリ、structuredContent に JSON（id/日時/雲量/bbox/アセットURL）を返す。

Args:
    collection: コレクションID（既定 "sentinel-2-l2a"）。stac_collections で確認可。
                例: "landsat-c2-l2", "sentinel-2-l1c", "sentinel-1-grd", "naip"。
    bbox: 空間範囲（"lon_min,lat_min,lon_max,lat_max"）。
    place: 地名（bbox より優先。Open-Meteo のジオコーディングで解決）。
    datetime: 時間範囲（"YYYY-MM-DD" または "start/end"）。省略で最近。
    max_cloud_cover: 雲量上限（%）（eo:cloud_cover を持つ場合）。
    limit: 返す件数（既定 5、最大 10）。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bboxNo
limitNo
placeNo
datetimeNo
collectionNosentinel-2-l2a
max_cloud_coverNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.25.2

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully declares authentication-free operation, describes the return shape (display summary in content, JSON in structuredContent with id/date/cloud cover/bbox/asset URL), notes that max_cloud_cover only applies when eo:cloud_cover exists, and sets a hard limit of 10. Missing details like rate limits or error behavior keep it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then examples, location handling, return format, and finally a clearly labeled Args section. Each part is useful, though the description is somewhat long; it remains well-organized and free of filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six parameters, no annotations, no output schema, and 0% schema coverage, the description is largely complete: it covers purpose, usage examples, alternatives, return structure, auth, and every parameter. It omits potential error cases or pagination behavior, but no output schema exists to cover those, so the gap is minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description fully compensates by documenting all six parameters: collection (default and examples), bbox (format), place (priority and geocoding source), datetime (accepted formats and default recency), max_cloud_cover (meaning and applicability condition), and limit (default 5, maximum 10).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (STAC検索する) and resource (衛星データ from AWS Earth Search), names supported collections, and explicitly points to the sibling stac_collections for collection ID lookup. An agent can distinguish it from other search tools by the AWS Earth Search source and satellite data focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides concrete example queries, explains the bbox/place alternative (place prioritized over bbox), and notes that stac_collections can be used to find collection IDs. It does not explicitly state when to prefer this over sibling search tools like uk_stac_search or copernicus_search, so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools