hospital-ratings-cms-star-ratings-mcp
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
hospital-ratings-cms-star-ratings-mcp
Hospital ratings for AI assistants: the CMS overall hospital star rating, patient survey (HCAHPS) stars, ER wait times and quality measures for every US hospital in Medicare Care Compare. Ask for the best rated hospitals in your city, how a hospital scores before surgery, or which of two hospitals has the shorter ER wait.
This is a Model Context Protocol (MCP) server. It reads the Medicare Care Compare hospital datasets that CMS publishes in the Provider Data Catalog on data.cms.gov at call time. It needs no API key.
Tools
Tool | What it returns |
| Hospitals in a state, city, county or ZIP code (or by name) with the CMS overall star rating, patient survey summary stars, type, ownership and ER availability, best rated first, with the count at each star level. Filters: hospital type, minimum stars, emergency services. |
| One hospital in full: overall star rating (or why it has none), mortality, safety and readmission measures better or worse than the national rate, patient survey stars overall and by topic, share rating it 9 or 10 and who would definitely recommend it against national, ER median time, left without being seen, sepsis care and staff flu vaccination against the state and national average. |
| 2 to 5 hospitals side by side on overall stars, patient stars, 9-10 ratings, ER median time, sepsis care and measure groups, with the leader on each. |
Every result has structured JSON, a plain-text summary, as_of, source and more (a page on mcpstamp.com). Every tool is marked read-only.
Related MCP server: medical-hospital-mcp-server
What it knows that your model does not
The current CMS overall hospital star rating for each of the 5,435 hospitals in the October 2026 Care Compare data and the reason when a hospital is not rated, from the latest Care Compare refresh rather than a training-time snapshot.
Patient survey (HCAHPS) star ratings by topic and the share of patients who rated the hospital 9 or 10, compared with the national average.
Each hospital's ER median time from arrival to leaving and its rate of patients who left before being seen, against the state and national averages.
Install
Hosted (custom connector, ChatGPT developer mode, any remote MCP client)
Paste this URL. No token, no sign-up.
https://hospital-ratings-cms-star-ratings-mcp.lipmichal.workers.dev/mcpCursor
Add to ~/.cursor/mcp.json.
{
"mcpServers": {
"hospital-ratings": { "url": "https://hospital-ratings-cms-star-ratings-mcp.lipmichal.workers.dev/mcp" }
}
}VS Code
Add to .vscode/mcp.json.
{
"servers": {
"hospital-ratings": { "type": "http", "url": "https://hospital-ratings-cms-star-ratings-mcp.lipmichal.workers.dev/mcp" }
}
}Local stdio
The npm package is not published. Build it from this repository with Node 20 or newer, then point your MCP client at node /path/to/hospital-ratings-cms-star-ratings-mcp/dist/stdio.js.
git clone https://github.com/theluckystrike/hospital-ratings-cms-star-ratings-mcp && cd hospital-ratings-cms-star-ratings-mcp
npm install && npm run build
node dist/stdio.jsExample prompts
"What are the best rated hospitals in Boston?"
"How good is Mass General? What is its CMS star rating and ER wait time?"
"Compare Brigham and Women's and Massachusetts General Hospital for patient satisfaction."
"Which hospitals in Vermont with an emergency room have 4 or 5 stars?"
Data sources
Full list in DATA_SOURCES.md.
CMS Provider Data Catalog (Medicare Care Compare), hospital datasets: https://data.cms.gov/provider-data/topics/hospitals
Limitations
US hospitals that report to Medicare only. Critical access, psychiatric, children's, cancer and DoD hospitals often have no overall star rating; the answer says why, using the CMS footnote.
Star ratings and measures cover past periods (patient survey and ER times for 2025 in the October 2026 refresh); CMS refreshes them quarterly.
Search is by state, city, county, ZIP code or ZIP prefix and name, not by distance.
Ratings are one input to choosing a hospital. Check the hospital on medicare.gov/care-compare and with a doctor.
More
More MCP servers that answer questions your assistant cannot answer alone are on mcpstamp.com.
Part of the Zovo MCP collection at https://mcp.zovo.one
Built by theluckystrike.
Development
npm install
npm test # builds, then runs the fixture tests and an offline stdio test
node scripts/stdio-transcript.mjs # live stdio round trip, writes .live/stdio-transcript.jsonlCI (.github/workflows/bundle.yml) runs the tests, the type check and wrangler deploy --dry-run --outdir out, and uploads the Worker bundle as an artifact.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Pay-per-call US healthcare data: hospital financials, prices, quality, exclusions, wages.
CMS quality ratings, payer-negotiated prices, and clinician data for 41K+ US healthcare facilities.
US healthcare data for AI agents: CMS, FDA adverse events, CDC, NPPES NPI. Keyless, real samples.
US healthcare public data, one endpoint: prices, Medicare, MA benefits, Stars, Medicaid, providers.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to search, query, and analyze CMS healthcare datasets from data.cms.gov, supporting features like dataset discovery, filtering, and CSV download for large-scale analysis.52MIT
- FlicenseNot gradedqualityCmaintenanceEnables hospital search and detail lookup to discover medical institutions and verify campuses, departments, contacts, introductions, and operating entities.1-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to discover, inspect, and query CMS open datasets covering Medicare/Medicaid provider, spending, enrollment, drug pricing, quality, hospital, nursing home, and ACO data. Supports keyword search, metadata lookup, paged row retrieval, full-text search, and exact-match column filters.88 npm1MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to query authoritative sources like FDA, WHO, PubMed, RxNorm, and Google Scholar for drug information, health statistics, clinical guidelines, trials, and medical literature. It runs locally with no API keys, so data stays private while results come back with evidence grading and resilient fallbacks.74 npmISC