DEM Terrain Analysis
AI-powered terrain analysis for any location on Earth. Uses super-resolution and computes environmental risk metrics including erosion, water flow, and a composite Site Intelligence Score.
README
DEM Terrain Analysis MCP Server
AI-powered terrain analysis using deep learning super-resolution. Analyze any location on Earth for environmental risk, erosion potential, water flow patterns, and more.
Tools
| Tool | Description |
|---|---|
analyze_terrain |
Get Site Intelligence Score and terrain metrics summary for any lat/lon |
get_full_terrain_data |
Get full super-resolved DEM + per-cell metric grids |
check_api_health |
Verify the API is running |
What it does
Given a latitude/longitude, this MCP server:
- Fetches 30m satellite elevation data
- Runs AI super-resolution to produce 10m terrain (3× detail enhancement)
- Computes 6 terrain analytics metrics including the Site Intelligence Score
Metrics
- flow_direction — water drainage direction per cell (D8 algorithm)
- flow_accumulation — upstream drainage count
- twi — Topographic Wetness Index (saturation tendency)
- erosion_risk — soil erosion susceptibility [0-1]
- runoff_potential — surface water runoff likelihood [0-1]
- site_intelligence_score — composite environmental risk [0-1]
Site Intelligence Score
A composite metric combining TWI, erosion risk, and runoff potential:
- 0.0–0.2: Low risk
- 0.2–0.4: Moderate
- 0.4–0.6: Elevated
- 0.6–0.8: High
- 0.8–1.0: Critical
Installation
{
"mcpServers": {
"dem-terrain": {
"command": "uvx",
"args": ["dem-terrain-mcp"]
}
}
}
Or run directly:
pip install dem-terrain-mcp
python -m dem_terrain_mcp
Example usage
Ask your AI assistant:
"Analyze the terrain at 48.7768, -121.8145 with a 500m bounding box"
Response includes elevation range, Site Intelligence Score with risk level, and all 6 terrain metrics.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| latitude | float | yes | [-90, 90] |
| longitude | float | yes | [-180, 180] |
| bbox_size_m | int | no | Bounding box in meters [250-5000], default 500 |
License
Proprietary. The terrain analysis API is a hosted service.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。