SWATGenX MCP Server
Enables search and retrieval of calibrated SWAT+ watershed models, national groundwater lithology and PFAS inventories, plus API-key-secured ordering and downloading of custom watershed models.
README
SWATGenX MCP Server
The agent-native front door to SWATGenX — automated, calibrated SWAT+ watershed modeling for the conterminous United States.
Add it to Claude or any MCP client and a continental watershed-modeling platform becomes a set of callable tools: search calibrated SWAT+ models, read calibration and held-out validation scores, query a national groundwater lithology inventory of ~28.8 million depth intervals, query a national PFAS monitoring inventory, and — with an API key — order and download watershed models.
- Endpoint:
https://www.swatgenx.com/mcp - Transport: streamable HTTP
- Full documentation & client setup: https://www.swatgenx.com/mcp-server
Connect
{
"mcpServers": {
"swatgenx": {
"type": "http",
"url": "https://www.swatgenx.com/mcp"
}
}
}
Six tools need no credentials. To order or download models, send your API key in the
X-SWATGenX-Api-Key header (free key with an account at swatgenx.com).
Tools
| Tool | What it does | Needs |
|---|---|---|
search_swat_models |
Browse the example-model catalog (state, size, calibration status) | — |
get_model_calibration |
Calibration and held-out validation NSE / PBIAS for one model | — |
query_groundwater |
Nearest wells and lithology from the national inventory | — |
query_pfas |
National PFAS monitoring inventory by state or analyte | — |
request_model |
Preview what SWATGenX would build for a gauge or HUC12 outlet | — |
get_access_info |
The access ladder and your current tier | — |
order_model |
Order a real SWAT+ build | API key |
get_order_status |
Track a build order to completion | API key |
list_my_models |
List your build orders | API key |
download_model |
Mint a 24-hour download link | API key |
About
SWATGenX builds physically based SWAT+ and coupled SWAT+/MODFLOW 6 models from NHDPlus HR hydrography, gSSURGO soils, NLCD land cover and PRISM climate, and calibrates them against USGS streamflow. The national groundwater inventory this server queries is described in a preprint under open review at Earth System Science Data (doi:10.5194/essd-2026-527).
The server implementation lives in the main SWATGenX repository; this repository holds the
registry manifest (server.json) and the publish workflow.
License
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。