How do I add official healthcare facility records to ChatGPT?
Add the zReports MCP server (https://api.zreports.org/mcp, no authentication) to ChatGPT in developer mode, or install the zReports app from the directory once it is listed, and ChatGPT answers facility questions from the official records: hospitals, surgery centers, nursing homes, hospice, dialysis, home health, psychiatric and rehab facilities, fertility centers and addiction treatment, each with the dataset, version and date. The same server works in Claude and any MCP client.
The difference it makes: Three frontier models sat the US HealthCare Exam. OpenAI 42, Anthropic 44 and Google 34 confident wrong answers out of 50. zBench, answering from official data, 50 of 50. The record condition in that exam was this API, so the answer ChatGPT gives with zReports attached is the same record the exam graded against. zReports' healthcare facility evaluation is now part of Stanford's MedHELM.
Ask "Which fertility clinic in Sacramento reports to CDC", "Is this nursing home fined", or "Which surgery center near me has the stronger record". When the publisher's file is silent, the answer says not published instead of guessing.
A free key is one email away on https://zreports.org/api: 500 calls a day, attribution to zReports required. Inside Claude or ChatGPT no key is needed.
Try it in thirty seconds
In Claude
- Settings, Connectors, Add custom connector
- Name zReports, URL https://api.zreports.org/mcp, no authentication
- Ask: "Which nursing home in Roseville CA has the stronger record"
In ChatGPT or any MCP client
- Add an MCP server with the URL https://api.zreports.org/mcp
- Four tools: find_facility, get_record, get_company, compare
- No key needed inside an assistant
The four tools
| Tool | Arguments | Example |
|---|---|---|
find_facilityFind US health facilities in the zReports facility file by name words, city, state, zip or category (hospital, nursing, asc, psych, rehab, hospice, dialysis, homehealth, fertility, addiction, daycare). Returns matches with the facility_id to pass to get_record or compare. "no match" is an answer: the facility is not in the publisher's file. | name?, city?, state?, zip?, category? | open an example |
get_recordReturn the official records of one facility: the highlight lines, the publisher's row verbatim (official_record), alternatives nearby in the same category, a buy_url for the zReport (which holds the zReports grade and zScore), and the source, version and as_of date. Lines the publisher does not carry read "not published". | facility_id | open an example |
get_companyReturn every facility the publisher lists under one chain or organization name, with counts by category and state, the average score, penalties and fines on record, and changes of ownership. Use for health systems, nursing home chains, dialysis chains and surgery center operators. | name, state? | open an example |
compareCompare two to five facilities side by side on the same published fields: status, ownership, beds, ratings, penalties, deficiencies where the publisher reports them. The zReports grade and zScore are in each facility's zReport. | facility_ids | open an example |
Questions
Do I need an API key in ChatGPT?
No. Inside an assistant the zReports channel needs no key. Direct REST calls from a product use a free or paid key from the /api page.
Is zReports affiliated with OpenAI?
No. zReports is available in ChatGPT through MCP; it is not affiliated with OpenAI or Anthropic.
Will ChatGPT show the zReports grade?
The publisher's own figures, yes. The zReports grade and zScore for any facility are in its zReport, and the answer carries the link to it.