Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-cms find CMS datasets on Medicare drug pricing and show me a few rows"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CMS Open Data MCP — US Centers for Medicare & Medicaid Services.
Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.
Tool | Description |
| Find CMS dataset IDs + titles by keyword. CMS publishes Medicare/Medicaid open data (provider data, spending, enrollment, drug pricing, quality measures, hospitals, nursing homes, ACOs, etc.). Searches the CMS DCAT catalog client-side over each dataset title/description/keywords. Returns the datasetId (UUID) you pass to get_dataset and dataset_info. |
| Pull rows from a CMS dataset by datasetId (UUID from search_datasets). Returns an array of row objects whose keys are the dataset columns. Supports paging (size/offset), full-text keyword search across the dataset, and exact-match column filters via filters: {COLUMN: VALUE} (column names match the keys in returned rows, e.g. {"State": "TX"}). |
| Metadata for a CMS dataset by datasetId: title, description, total row count, last-modified date, themes/keywords, and downloadable resources (CSV files, data dictionaries). Use after search_datasets to inspect a dataset before pulling rows. |
Related MCP server: OpenFDA FastMCP Server
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"cms": {
"url": "https://gateway.pipeworx.io/cms/mcp"
}
}
}tools/list at https://gateway.pipeworx.io/cms/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 1683+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
curl -X POST https://gateway.pipeworx.io/v1/tools/cms_search_datasets \
-H 'Content-Type: application/json' \
-d '{"keyword":"hospital"}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/cms_search_datasets. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"cms": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-cms"]
}
}
}Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-cmsIt speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call
for only this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
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 Cms data" })The gateway picks the right tool and fills the arguments automatically.
MIT
This server cannot be deployed
US healthcare data for AI agents: CMS, FDA adverse events, CDC, NPPES NPI. Keyless, real samples.
CMS Open Payments, with annual dataset discovery through the official DKAN API.
CMS quality ratings, payer-negotiated prices, and clinician data for 41K+ US healthcare facilities.
US healthcare data for AI agents: prices, Medicare Advantage, Medicaid, providers, drugs. Receipted.
