Name: Health Gorilla
Author: usefulapi

Health Gorilla MCP

Query Health Gorilla FHIR patients, conditions, medications and lab results.

Tool-list grade A Remote · Streamable HTTP No auth needed 16 tools v1.11.1

No reviews yet by usefulapiGitHub The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Query Health Gorilla FHIR patients, conditions, medications and lab results.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http health-gorilla-mcp https://health-gorilla.usefulapi.io/mcp

# 2 — ask your agent for something these tools do
#   healthgorilla_find_patients, healthgorilla_get_patient, healthgorilla_get_patient_everything and 13 more

Health Gorilla costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

usefulapi334 servers

24 categories

All 334 servers

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Search for patients by demographics. FHIR: GET /Patient?given=&family=&birthdate=&identifier=. Returns a FHIR searchset Bundle. Use the returned Patient id with the other tools.

Parameter	Type	Required	Notes
given	string	no	Given (first) name.
family	string	no	Family (last) name.
birthdate	string	no	Date of birth, yyyy-mm-dd.
identifier	string	no	Business identifier (e.g. MRN), optionally system\|value.
_count	integer	no	FHIR _count — max results per page.

Read a single patient by id. FHIR: GET /Patient/{id}. Returns a FHIR Patient resource.

Parameter	Type	Required	Notes
patient_id	string	yes	Health Gorilla Patient resource id.

Fetch the comprehensive record for a patient as a FHIR Bundle. FHIR: GET /Patient/{id}/$everything. Optionally scope by _since and page with _count.

Parameter	Type	Required	Notes
patient_id	string	yes	Health Gorilla Patient resource id.
_since	string	no	Only include resources updated on/after this date, yyyy-mm-dd.
_count	integer	no	FHIR _count — max results per page.

List a patient's conditions/problems. FHIR: GET /Condition?patient={id}. Returns a FHIR searchset Bundle.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id.
category	string	no	Condition category, e.g. problem-list-item, encounter-diagnosis.
_count	integer	no	FHIR _count — max results per page.

List a patient's medication requests/prescriptions. FHIR: GET /MedicationRequest?patient={id}. Returns a FHIR searchset Bundle.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id.
status	string	no	Medication status, e.g. active, completed, stopped.
_count	integer	no	FHIR _count — max results per page.

List a patient's allergies/intolerances. FHIR: GET /AllergyIntolerance?patient={id}. Returns a FHIR searchset Bundle.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id.
_count	integer	no	FHIR _count — max results per page.

List a patient's immunizations. FHIR: GET /Immunization?patient={id}. Returns a FHIR searchset Bundle.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id.
_count	integer	no	FHIR _count — max results per page.

List a patient's observations (labs, vitals). FHIR: GET /Observation?patient={id}. Filter by category (e.g. laboratory, vital-signs), LOINC code, or date. Returns a FHIR searchset Bundle.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id.
category	string	no	Observation category, e.g. laboratory, vital-signs.
code	string	no	Observation code (e.g. LOINC), optionally system\|value.
date	string	no	Date filter (FHIR date param, may use prefixes like ge2026-01-01).
_count	integer	no	FHIR _count — max results per page.

List a patient's diagnostic reports (lab panels, imaging). FHIR: GET /DiagnosticReport?patient={id}. Returns a FHIR searchset Bundle.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id.
category	string	no	Report category, e.g. LAB, RAD.
_count	integer	no	FHIR _count — max results per page.

List a patient's document references (C-CDA, notes, etc). FHIR: GET /DocumentReference?patient={id}. Each entry points at a Binary you can fetch with healthgorilla_get_binary.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id.
type	string	no	Document type code (e.g. LOINC), optionally system\|value.
_count	integer	no	FHIR _count — max results per page.

List a patient's insurance coverage. FHIR: GET /Coverage?patient={id}. Returns a FHIR searchset Bundle.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id.

Retrieve raw document content by Binary id. FHIR: GET /Binary/{id}. Content may be a FHIR Binary JSON resource, XML C-CDA, or base64 — returned as-is (raw text if not JSON).

Parameter	Type	Required	Notes
binary_id	string	yes	Binary resource id (from a DocumentReference).

Poll a RequestResult URL returned by healthgorilla_start_patient360_query. HTTP 202 = still processing, 200 = done (returns retrieval metrics: organizationsTotal, documentsFound, documentsImported, documentsSkipped, documentsFailed). Returns { status, body }.

Parameter	Type	Required	Notes
request_result_url	string	yes	The RequestResult poll URL returned by a Patient360 query (a Health Gorilla URL).

Escape hatch: run an arbitrary FHIR search. GET /{resource_type}?{query}. e.g. resource_type='Observation', query='patient=123&category=laboratory&_count=5'. Use when a dedicated tool does not cover your query.

Parameter	Type	Required	Notes
resource_type	string	yes	FHIR resource type, e.g. Patient, Observation, Encounter.
query	string	no	Raw FHIR query string without the leading '?', e.g. patient=123&_count=5.

Registers a NEW patient record in your Health Gorilla tenant. FHIR: POST /Patient with a minimal FHIR R4 Patient resource built from the given args. State-changing.

Parameter	Type	Required	Notes
given	string	yes	Given (first) name.
family	string	yes	Family (last) name.
birthdate	string	yes	Date of birth, yyyy-mm-dd.
gender	string	yes	Administrative gender.
line	string	no	Street address line.
city	string	no	City.
state	string	no	State (2-letter).
postalCode	string	no	Postal / ZIP code.
identifier	string	no	Business identifier value (e.g. MRN).

Initiates an asynchronous national-network records retrieval (CommonWell / Carequality / QHINs) that imports external documents into your tenant. FHIR: GET /DocumentReference/$p360-retrieve?patient={id} with header 'Prefer: respond-async'. Returns the RequestResult poll URL (Location header); poll it with healthgorilla_poll_query_status. State-changing.

Parameter	Type	Required	Notes
patient_id	string	yes	Patient resource id to retrieve external records for.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Health Gorilla or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.11.1 · scanned 20 Oct 2026

Graded from the tools this server lists, not from its source code.

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings0 threat · 0 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digestd2edc5558eb818cb2d574c13a28b8ec11d7dc9512a279a62e726a6c87b5f5e51

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
healthgorilla_find_patients	no tags
healthgorilla_get_patient	no tags
healthgorilla_get_patient_everything	untrusted-input	untrusted-input: keyword "fetch"
healthgorilla_list_conditions	no tags
healthgorilla_list_medications	no tags
healthgorilla_list_allergies	no tags
healthgorilla_list_immunizations	no tags
healthgorilla_list_observations	no tags
healthgorilla_list_diagnostic_reports	no tags
healthgorilla_list_documents	untrusted-input	untrusted-input: keyword "fetch"
healthgorilla_get_coverage	no tags
healthgorilla_get_binary	no tags
healthgorilla_poll_query_status	no tags
healthgorilla_fhir_search	no tags
healthgorilla_create_patient	state-write	state-write: declares destructiveHint: true
healthgorilla_start_patient360_query	state-write	state-write: declares destructiveHint: true

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestd2edc5558eb818cb

Scanned2026-10-20

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.

Where are you running it?

Tool surface

Release history

Health Gorilla MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also