apibase

CMS — US Hospital Search

cms.hospital.search

Read-onlyIdempotent

Search 5 400+ US hospitals in the CMS Provider Data catalog with quality star ratings (1–5 stars). Filter by state, city, ZIP code, hospital name, hospital type (Acute Care, Critical Access, Childrens, Psychiatric, Rehabilitation), and minimum overall rating. Returns CMS Certification Number (CCN), facility name, address, phone, hospital type, ownership, emergency services flag, and overall star rating. Star ratings are composite scores from CMS Hospital Compare — 5 stars = top quality. Covers all Medicare/Medicaid-certified hospitals. No auth — US Centers for Medicare & Medicaid Services public domain, unlimited free.

Input Schema

TableJSON Schema

Name	Required	Description
`city`	No	City or town name to filter hospitals (partial match, case-insensitive). Example: "Los Angeles", "Boston".
`name`	No	Partial hospital name to search (case-insensitive substring match). Example: "Memorial", "General Hospital", "St. Mary".
`limit`	No	Maximum number of hospitals to return (1–100, default 20).
`state`	No	Two-letter US state abbreviation to filter hospitals (e.g. CA, NY, TX). Returns all hospitals in the state when specified.
`offset`	No	Number of results to skip for pagination (default 0).
`zip_code`	No	5-digit US ZIP code to filter hospitals by location. Example: "90210", "10001".
`min_rating`	No	Minimum CMS Overall Hospital Star Rating (1–5 stars). Filter to only return hospitals with rating >= this value. Example: 4 returns 4-star and 5-star hospitals only.
`hospital_type`	No	Filter by hospital type classification. Most common: "Acute Care Hospitals" (general hospitals), "Critical Access Hospitals" (rural/small), "Childrens" (pediatric).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`error`	No	Present only when the call failed. Includes error code, message, request_id, and any provider-specific extras.
`result`	No	Tool response payload. Shape varies per tool — consult the tool description and inputSchema. May be an object, array, string, or number depending on the upstream provider response.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 22, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds meaningful context: the data source (CMS Provider Data), the rating scale (5 stars = top quality), and access details (no auth, public domain, unlimited free). It also notes the scope (all Medicare/Medicaid-certified hospitals). These go beyond the annotations and help the agent understand behavior and constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and then details filters and returns. It is concise but comprehensive, using lists and examples without unnecessary fluff. Every sentence adds information about usage, scope, or output.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with 8 optional parameters and an output schema, the description covers the key aspects: what it does, what filters exist, what it returns, and access constraints. It does not explicitly mention pagination, but that is handled by limit/offset in the schema. The description is complete enough for an agent to correctly invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are well-documented. The description adds value by explaining the star rating meaning and giving examples of hospital types (Acute Care, Critical Access, Childrens, etc.). It also clarifies that filters include city, ZIP, name, type, and rating, which complements the schema without redundancy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches 5,400+ US hospitals in the CMS Provider Data catalog with star ratings, listing specific filters and return fields. It is unambiguous about the resource (hospitals) and action (search), and distinct from sibling tools like cms.dialysis.search or cms.nursing_home.search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes it obvious that this tool is for hospital data, and siblings are for other provider types, so the use case is clear. However, it does not explicitly say 'use this for hospitals, not for nursing homes,' though the context strongly implies it. It also explains coverage of all Medicare/Medicaid-certified hospitals, which helps an agent decide when to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All apibase tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.