MCP server exposing 3 tools for healthdata.
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/healthdata/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}
search_datasets — Search HealthData.gov for public-health datasets by keyword (e.g. "COVID hospitalizations", "Medicare spending", "opioid prescriptions"). Returns each dataset's Socrata id (a 4x4 like "g62h-syeh"), title, description, owning agency, tags, when the data was last updated, and its page-view count. Pass the id to get_dataset for full metadata or to get_rows to read the actual rows.get_dataset — Full metadata for one HealthData.gov dataset by its Socrata id (a 4x4 like "g62h-syeh", returned by search_datasets). Returns title, description, owning agency, licence, every column with its type, row count and the last data update. NOTE: HealthData.gov migrated off CKAN, so an old CKAN package id or slug will NOT resolve — search for the dataset again to get its 4x4.get_rows — Read actual rows from a HealthData.gov dataset by its Socrata 4x4 id. Optional SoQL `where` (e.g. "state = 'CA'") and `order` (e.g. "date DESC"). Use get_dataset first to see the column names. This returns the DATA, not a download link.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/healthdata/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io