MCP server exposing 2 tools for jhtdb.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/jhtdb/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}
jhtdb_datasets — Catalog of Johns Hopkins Turbulence Databases (JHTDB) datasets available for point queries — forced isotropic turbulence, channel flow, MHD turbulence, transitional boundary layer, atmospheric boundary layer and wind-farm LES, and more. Each entry gives the dataset code to pass to jhtdb_point_query, its spatial domain (x/y/z ranges, in the dataset's native simulation units), grid resolution, time range, and which physical fields (velocity, pressure, magnetic field, temperature, ...) it carries.jhtdb_point_query — Interpolated velocity, pressure, or velocity-gradient values at up to 10 points and a single time in a Johns Hopkins Turbulence Databases (JHTDB) reference DNS/LES dataset. Values are returned in the dataset's native simulation units (dimensionless DNS code units for the isotropic/channel/MHD datasets; physical meters/seconds for the atmospheric-boundary-layer and wind-farm LES datasets) — call jhtdb_datasets first to see a dataset's domain and time range. Uses JHTDB's public testing authorization token, capped well under its documented small-query allowance.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/jhtdb/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io