For AI agents
SWATGenX has an MCP server
A public Model Context Protocol server over streamable HTTP. Add it to Claude or any MCP client and a continental watershed-modeling platform becomes 10 callable tools — 6 of them with no credentials at all.
- 10 tools
- Read tools need no key
- National groundwater + PFAS data
Does SWATGenX have an MCP server?
Yes. SWATGenX runs a public Model Context Protocol server at https://www.swatgenx.com/mcp, over the streamable-HTTP transport. Add it to Claude or any MCP client and the platform becomes 10 callable tools. 6 of them need no credentials; ordering a model and minting download links use an API key.
Most scientific platforms make an agent scrape a web app or reverse-engineer an API. SWATGenX exposes the platform directly: the same models, the same national datasets and the same quotas that the web application uses, as tools an agent can call.
How do I connect Claude to SWATGenX?
Add https://www.swatgenx.com/mcp as a streamable-HTTP MCP server in your client configuration. No install, no local process, no scraping. Public-data tools work immediately; to order or download models, send your API key in the X-SWATGenX-Api-Key header.
The endpoint — nothing to install, no local process:
https://www.swatgenx.com/mcp (transport: streamable HTTP)
Client configuration:
{
"mcpServers": {
"swatgenx": {
"type": "http",
"url": "https://www.swatgenx.com/mcp"
}
}
}To order or download models, send your API key as a header:
X-SWATGenX-Api-Key: <your key>
Keys come from your access settings. The server is also advertised to agents in this site's llms.txt.
What tools does the server expose?
10 tools. The read side is open to any agent; only building and downloading models consume an allocation.
What data can an agent query?
A national groundwater inventory of about 28.8 million depth-resolved lithology intervals harmonized from state well registries, a national PFAS monitoring inventory, and the SWAT+ example-model catalog with calibration and validation statistics for each model. All of it is derived from public agency sources with provenance retained.
The groundwater inventory is described in a preprint under open review at Earth System Science Data. Nothing is interpolated or gap-filled; every record traces to the agency that published it.
Common questions
What can an AI agent do with SWATGenX?
Without any credentials an agent can search the SWAT+ example-model catalog, read calibration and held-out validation scores, query the national groundwater inventory of 28.8 million lithology intervals, query the national PFAS monitoring inventory, and preview what a model of a given watershed would contain. With an API key it can order a real SWAT+ build, track it, and download the finished model package.
Is the SWATGenX MCP server free?
The read tools are open and free — catalog search, calibration results, groundwater and PFAS queries, and build previews need no account. Ordering models consumes the same fair-use allocation as the web application and the REST API, so an agent cannot exceed what its user is entitled to.
Does the MCP server let an agent build a watershed model?
Yes, with an API key. An agent calls order_model with a USGS gauge number, a HUC12 outlet or a HUC8 code, tracks the build with get_order_status, and retrieves the finished SWAT+ package with download_model. The build runs the same pipeline as the web application — NHDPlus HR hydrography, gSSURGO soils, NLCD land cover and PRISM climate.
Three ways in
MCP is one of three doors onto the same platform — the others are the REST API and the swatgenx Python package. Same national data, same SWAT+ and MODFLOW 6 models, same quotas.