{
  "markdown": "# mcp-cms\n\nCMS Open Data MCP — US Centers for Medicare & Medicaid Services.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `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. |\n| `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\"}). |\n| `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. |\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"cms\": {\n      \"url\": \"https://gateway.pipeworx.io/cms/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/cms/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Cms data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 3257,
  "sha": "b6a1db8277a7a745bef8d995d3dea60cbac3d61650e3aa8f24f7ee9622cada3c",
  "repo_slug": "pipeworx-io/mcp-cms",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_cms_0ef913d3/readme"
}