Where is a US hospital's CMS price-transparency file? The URL, quoted from its own cms-hpt.txt.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Which hospitals does this health system publish prices for? Give a domain ("mercy.net", "www.adventhealth.com", or a URL on it) and get every location its root cms-hpt.txt names, each with its machine-readable file URL, its public page and the line it was read from. This is how the files are actually published — one cms-hpt.txt can declare eighty-six hospitals — so it is the right call when you know the system but not the exact location name. With no domain it lists the 73 domains this register covers, with a count for each.
How many locations to return, 1–20. Default 20.
The health system's domain. Scheme, "www." and any path are ignored, so "https://www.mercy.net/billing" and "mercy.net" are the same system. Omit it to list the domains covered.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http hospital-price-transparency-files https://referencesource.org/mcp/hospitals
Which hospitals does this health system publish prices for? Give a domain ("mercy.net", "www.adventhealth.com", or a URL on it) and get every location its root cms-hpt.txt names, each with its machine-readable file URL, its public page and the line it was read from. This is how the files are actually published — one cms-hpt.txt can declare eighty-six hospitals — so it is the right call when you know the system but not the exact location name. With no domain it lists the 73 domains this register covers, with a count for each.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many locations to return, 1–20. Default 20. |
| domain | string | The health system's domain. Scheme, "www." and any path are ignored, so "https://www.mercy.net/billing" and "mercy.net" are the same system. Omit it to list the domains covered. |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "How many locations to return, 1–20. Default 20."
},
"domain": {
"type": "string",
"description": "The health system's domain. Scheme, \"www.\" and any path are ignored, so \"https://www.mercy.net/billing\" and \"mercy.net\" are the same system. Omit it to list the domains covered."
}
}
}Where is this hospital's CMS standard-charges machine-readable file? Give a hospital name or part of one ("Prisma Health Richland", "Pennsylvania Hospital", "Abbott Northwestern") and get the file URL, the hospital's public price-transparency page, the health-system domain whose cms-hpt.txt declared it, and the verbatim line it was read from. Punctuation and case are ignored when matching. Hospital names are not unique — 64 names in this register belong to more than one hospital — so this returns a list and the domain tells them apart. Use list_hospitals_on_domain when you know the system rather than the hospital.
| Argument | Type | Description |
|---|---|---|
| name* | string | Hospital name or part of one. Case- and punctuation-insensitive; exact matches are returned first, then names starting with it, then names containing it. |
| limit | integer | How many to return, 1–20. Default 20. |
| domain | string | Optional health-system domain to narrow by, e.g. "mercy.net" or "https://www.mercy.net". Use it when a name matched more than one hospital. |
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Hospital name or part of one. Case- and punctuation-insensitive; exact matches are returned first, then names starting with it, then names containing it."
},
"limit": {
"type": "integer",
"description": "How many to return, 1–20. Default 20."
},
"domain": {
"type": "string",
"description": "Optional health-system domain to narrow by, e.g. \"mercy.net\" or \"https://www.mercy.net\". Use it when a name matched more than one hospital."
}
}
}Is this right? Check a claim about a hospital's price-transparency file — the machine-readable file URL, the public page, the domain — against the register instead of trusting it. Says whether the claim matches a stored value, appears only in the verbatim source quote, or differs (and then what the register says instead), and returns the source and quote so it can be traced upstream. Use it on a URL a model produced from memory: these URLs are long, they rot, and a plausible wrong one is indistinguishable from a right one until it is checked.
| Argument | Type | Description |
|---|---|---|
| field | string | Which field the claim is about, if you know it. Without it, every stored field of the record is checked. |
| domain | string | Optional health-system domain, needed when the name belongs to more than one hospital (64 names in this register do). |
| hospital* | string | The hospital name the claim is about, as resolve_hospital_mrf returns it. |
| claimed_value* | string | The value to check, exactly as claimed, e.g. "Terminated" or "2026-10-29". |
{
"type": "object",
"required": [
"claimed_value",
"hospital"
],
"properties": {
"field": {
"type": "string",
"description": "Which field the claim is about, if you know it. Without it, every stored field of the record is checked."
},
"domain": {
"type": "string",
"description": "Optional health-system domain, needed when the name belongs to more than one hospital (64 names in this register do)."
},
"hospital": {
"type": "string",
"description": "The hospital name the claim is about, as resolve_hospital_mrf returns it."
},
"claimed_value": {
"type": "string",
"description": "The value to check, exactly as claimed, e.g. \"Terminated\" or \"2026-10-29\"."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 16, 2026.