"CSS" matching MCP servers:

Exposes four CMS public datasets as callable tools in Claude conversations, enabling natural-language real-world evidence analytics without SQL expertise.

Provides read-only access to CMS Medicare inpatient DRG data via typed MCP tools and a guarded SQL interface over a DuckDB warehouse.

Enables AI agents and compatible MCP clients to submit inpatient medical-record front-page codes and receive deterministic MDC/ADRG/DRG grouping for CHS-DRG 2.0 and 3.0, including severity, status, and trace. Also supports diagnostic/procedure code lookup, batch grouping, and rule-version queries.

Enables MCP clients to discover and invoke domain-specialized tools for humanitarian emergency response, public health, research synthesis, grant proposals, human rights monitoring, maternal health, and SOP synthesis. It supports JSON-RPC 2.0 over Streamable HTTP for structured, privacy-conscious field outputs and voice-friendly summaries.

A remote MCP server that lets an LLM explore, query, aggregate, and benchmark the ~234 datasets in the CMS Provider Data Catalog — hospitals, dialysis facilities, nursing homes, home health, hospice, physicians, and more — in plain language.

Enables AI assistants to query FDA drug labels, FAERS adverse event reports, recalls, and ClinicalTrials.gov trials, and to compute pharmacovigilance signal metrics such as PRR/ROR with confidence intervals and flags. It also provides a drug safety brief prompt that combines these sources with source links and limitations.