NHANES (design-correct survey analysis) runs on your own machine — the client starts it, so there is no endpoint to ping. 103 installs a week from pypi. Last commit 5 Oct 2026.
Design-correct NHANES analysis: survey weights, pooled cycles, CIs and NCHS reliability flags.
Today is the operative word: we check NHANES (design-correct survey analysis) every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add nhanes-mcp -- uvx nhanes-mcp
{
"mcpServers": {
"nhanes-mcp": {
"command": "uvx",
"args": [
"nhanes-mcp"
]
}
}
}
[mcp_servers.nhanes-mcp]
command = "uvx"
args = ["nhanes-mcp"]
{
"mcpServers": {
"nhanes-mcp": {
"command": "uvx",
"args": [
"nhanes-mcp"
]
}
}
}
{
"servers": {
"nhanes-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"nhanes-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
NHANES_MCP_CACHE (Folder for downloaded NHANES files (default ~/.cache/nhanes-mcp)), NHANES_MCP_DATA_DIR (Folder of manually downloaded .xpt files, for offline use).
Live reliability for AI agent tools: is it working right now, and how do I call it correctly?
Customer research analysis and AI usability testing on any website or design.
MCP server for terrain analysis: DEM slope/aspect/suitability and point-cloud reading/gridding
Model work domains, score tasks for AI suitability, and design organisations.
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
Analyze Zigpoll survey responses, track trends, and get AI-powered insights.
AI-assisted MCP server for JSTQB-based test planning, design, review, and analysis.
Product analytics, user and company insights, surveys and NPS, reports, dashboards, and more.
Answers built from our own checks of this server.