
Connects Claude to the CMS National Provider Identifier registry, the official database of healthcare providers in the U.S. You get one tool, get_provider, which fetches a provider record by their 10-digit NPI. This is the go-to when you're building healthcare workflows that need to verify credentials, look up taxonomy codes, or pull practice location details. It's part of the Pipeworx gateway, so you can add it standalone or bundle it with their 673+ other data sources. Runs over streamable HTTP, so no local processes to manage. Useful for compliance checks, provider directories, or any app that needs authoritative healthcare practitioner data.
CMS NPI Registry MCP — every US healthcare provider with a National Provider Identifier (~7M individuals + organizations). No auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
search(number?, name?, first_name?, last_name?, organization_name?, taxonomy?, city?, state?, postal_code?, country_code?, npi_type?, address_purpose?, limit?, skip?)get_provider(npi) — convenience: lookup by 10-digit NPIhttps://npiregistry.cms.hhs.gov/api/?version=2.1 — public REST.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"npi-registry": {
"url": "https://gateway.pipeworx.io/npi-registry/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/npi-registry/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Npi Registry data" })
The gateway picks the right tool and fills the arguments automatically.
MIT