eve-esa/mcp-tool-registry

Developer tools

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

8 stars 11 forks Качество 81 Тренд 36Apache-2.0

Repository Install

This repository contains tools developed by the EVE team and the community

Обзор

The Model Context Protocol (MCP) is an open standard that lets an AI agent discover and call external tools. This repository is the tool registry of EVE, the Earth Virtual Expert: a collection of MCP servers for Earth Observation (EO) and Earth Science, written by the EVE team and the community. - Each server in servers/ is self-contained: a FastMCP entrypoint, pinned requirements and optional tests. - CI validates the structure, lints the code, scans for secrets and builds the container. - Merged servers are deployed to AWS Bedrock AgentCore and become tools for the EVE agent. Anyone building EO agents can run these servers locally or contribute a new one. Requires Python 3.13. Each server has its own requirements, so install only the one you need: Servers that need credentials ship a .env.template: copy it to .env in the same folder and fill it in. Some also accept them per request as HTTP headers, see Per-request credential headers.

README

Показан фрагмент оригинального README. Открыть оригинал.

About

One folder per server. Each server in servers/ is self-contained: a FastMCP entrypoint, pinned requirements and optional tests.
Checked on every pull request. CI validates the structure, lints the code, scans for secrets and builds the container.
Deployed to EVE. Merged servers are deployed to AWS Bedrock AgentCore and become tools for the EVE agent.

Anyone building EO agents can run these servers locally or contribute a new one.

Servers

Server	What it does	Tools	Credentials
`cdse`	Sentinel-1, -2, -3, -5P, Landsat and DEM imagery from the Copernicus Data Space Ecosystem (Sentinel Hub)	`fetch_sentinel1_grd`, `fetch_sentinel2`, `fetch_sentinel3_olci`, `fetch_sentinel3_slstr`, `fetch_sentinel3_syn_l2`, `fetch_sentinel5p_l2`, `fetch_landsat_ot_l1`, `fetch_dem`	CDSE client
`effis`	Burnt areas from EFFIS and Sentinel-2 burn metrics (NDVI, NBR, BAIS2)	`geocode_place`, `get_effis_burnt_areas`, `compute_metrics`	CDSE client
`eodashboard`	ESA / NASA / JAXA EO Dashboard narratives and indicators, resolved to STAC items	`list_narratives`, `search_narratives`, `get_narrative_content`, `list_themes`, `get_narrative_indicators`, `search_collections`, `get_collection_items`, `find_narratives_for_indicator`	none
`eotdl`	Search datasets, models and pipelines on the EO Training Data Lab	`eotdl_search`	none
`esa_moocs`	Semantic search over ESA Earth Observation MOOC transcripts	`search_moocs`	none

Открыть полный README на GitHub

Установка

This server does not publish a one-line install command.

Open the repository installation guide Новичок в MCP? Начните с руководства на mcpskill.org →

Конфигурация

{
  "mcpServers": {
    "geocode": {
      "command": "/absolute/path/to/mcp-tool-registry/.venv/bin/python",
      "args": ["/absolute/path/to/mcp-tool-registry/servers/geocode/server.py", "--transport", "stdio"]
    }
  }
}