cms 3 tools

MCP server exposing 3 tools for cms.

Endpoint

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/cms/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list"}

search_datasets — 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.
get_dataset — 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"}).
dataset_info — 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.

Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/cms/

Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io