Turbulence Modeling Resource MCP server

@pipeworx/turbulence-modeling-resource

Catalog of NASA Langley's standard turbulence-model verification and validation test cases (flat plates, airfoils, jets, a backward-facing step, the wall-mounted hump, shock/boundary-layer interactions, and more), plus reference data for the cases that publish an unambiguous experimental or correlation dataset.

Part of Pipeworx — an MCP gateway connecting AI agents to 1851+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

flow regime, documented Mach/Reynolds conditions, and whether reference data is available via tmrreferencedata.

• tmr_cases(...) — the full case catalog (or one category): id, category,

data for one case, where the case's own page unambiguously labels a file as the reference data rather than one of many turbulence-model CFD results.

• tmrreferencedata(...) — the reference (experimental or correlation)

Auth

Keyless. US government work — public domain.

Data sources

set of verification cases (checking that a turbulence model is implemented correctly) and validation cases (checking that it reproduces real flow physics) used across the turbulence-modeling community: flat plates, bumps-in-channel, 2D and 3D airfoils, axisymmetric jets, a backward-facing step, a wall-mounted hump, shock/boundary-layer interactions, a supersonic square duct, the ONERA M6 wing, and a high-Reynolds-number channel flow.

• NASA Langley Research Center, Turbulence Modeling Resource — the standard

The resource moved from its original NASA-hosted address to a GitHub Pages site the publisher itself maintains; this pack reads from the current address. Mach number and Reynolds number in the case catalog are filled in only where a case's own page states them explicitly — a null means NASA's page did not give that figure, not that the flow has no such condition.

Case directories hold dozens of files each — one per turbulence model's CFD result, plus (for some cases) the actual experimental or correlation reference data the models are checked against, named and linked distinctly on the case's own page. tmrreferencedata only serves the latter kind, and only for cases where that distinction is unambiguous from the page itself; everything else stays unmapped rather than guessed at, which is why only a handful of cases report reference_data: true today. Every file follows the same plain-text, Tecplot-style convention: #-prefixed comment lines, a variables="col1","col2",... header, optional zone, t="label" sections, then whitespace-separated numeric rows — parsed generically in src/index.ts rather than per-case.

tmrreferencedata's dataasof is the upstream file's own Last-Modified response header — never a date written into the pack at build time, which would silently go stale. fetchedat is always this call's own timestamp, so a caller still knows when Pipeworx last asked even on the rare response without a Last-Modified header. tmrcases' catalogtranscribed is a different thing entirely: the case list and conditions are a plain array transcribed from the publisher's pages at pack-build time, not re-fetched live on every call, so it is named and dated separately rather than borrowing dataas_of's meaning.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "turbulence-modeling-resource": {
      "url": "https://gateway.pipeworx.io/turbulence-modeling-resource/mcp"
    }
  }
}

What this endpoint actually serves

Shortened. The full README is on GitHub.