accueil / serveurs / Dev & Code / io.github.medprice-ai/mcp-medprice-ai
io.github.medprice-ai/mcp-medprice-ai
serveur MCP (Model Context Protocol) · mcp-medprice-ai 0.0.1
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.
Est-ce que io.github.medprice-ai/mcp-medprice-ai est sûr ?
Au dernier audit MCP Hub, le serveur MCP « io.github.medprice-ai/mcp-medprice-ai » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.
Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.
Les 6 outils
- batch_get_hospital_chargemaster_cost≈ 1104 tokens
Looks up cost stats for several (code_type, code) pairs at one hospital (identified by hospital_id) in a single call - the batch counterpart to get_hospital_chargemaster_cost. Use this instead of calling get_hospital_chargemaster_cost once per code when pricing a fixed set of codes at one hospital (e.g. cross-linking a curated list of procedures on a hospital's page). Capped at 100 codes per call; a request over that is rejected with INVALID_ARGUMENT rather than silently truncated.
Paramètres, retour & exemple (3)
Paramètrescodes· array · requis
The (code_type, code) pairs to price at this hospital - up to 100 entries. Results come back in this same order.hospital_id· string · requis
Opaque hospital identifier from list_hospitals.revision_id· string · optionnel
Optional. A revision_id from list_hospitals' per-hospital revisions array, to price that specific past revision instead of the hospital's latest one, applied to every code in this batch. Omit to use the latest revision.
Exemple d'appel{"name": "batch_get_hospital_chargemaster_cost", "arguments": {"codes": [], "hospital_id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": []}} - get_code_price_distribution≈ 1818 tokens
Returns the distribution of every hospital's price for a code_type/code, computed server-side: min/p10/q1/median/q3/p90/max, standard deviation, a histogram, and the real hospital nearest each percentile. Use this instead of paging through list_hospital_code_costs when you want to know how prices spread across hospitals (e.g. "is $12k high for MS-DRG 788?" - pass reference_price to get the number of hospitals priced below it). All figures are in terms of the chosen statistic (default: each hospital's average price).
Paramètres, retour & exemple (7)
Paramètrescode· string · requisbin_count· integer · optionnel
Number of histogram bars. Defaults to 16, capped at 200 (larger values are rejected).code_type· string · requis
Code system the billing code belongs to, e.g. APR-DRG, CDM, CPT, HCPCS, MS-DRG, RC.statistic· string · optionnel · PRICE_STATISTIC_AVERAGE | PRICE_STATISTIC_MEDIAN | PRICE_STATISTIC_MIN | PRICE_STATISTIC_MAX
Which per-hospital figure to distribute: each hospital's average (default), median, lowest filed price, or highest filed price.methodology· string · optionnel · case rate | fee schedule | other | percent of total billed charges | per diem
Pricing methodology. Omit to aggregate across all methodologies.reference_price· number · optionnel
Optional price to place on the distribution. When positive, hospitals_below_reference counts hospitals priced strictly below it. Negative values are rejected.min_sample_count· integer · optionnel
Minimum pricing sample size: only include hospitals whose price is backed by at least this many billing records (same semantics as list_hospital_code_costs). 0 (default) disables the filter. Negative values are rejected.
Exemple d'appel{"name": "get_code_price_distribution", "arguments": {"code": "texte", "code_type": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"q1": 1, "q3": 1, "max": 1, "min": 1, "p10": 1, "p90": 1, "median": 1, "std_dev": 1, "q1_hospital": {}, "q3_hospital": {}, "histogram_hi": 1, "histogram_lo": 1}} - get_hospital_chargemaster_cost≈ 861 tokens
Lookup hospital chargemaster cost
Paramètres, retour & exemple (5)
Paramètrescode· string · requiscode_type· string · requis
Code system the chargemaster/billing code belongs to, e.g. APR-DRG, CDM, CPT, HCPCS, MS-DRG, RC. Hospitals may also support additional proprietary code types not listed here.hospital_id· string · requis
Opaque hospital identifier from list_hospitals.revision_id· string · optionnel
Optional. A revision_id from list_hospitals' per-hospital revisions array, to price that specific past revision instead of the hospital's latest one. Omit to use the latest revision.methodologies· array · optionnel
Pricing methodologies to price, one result per entry in request order. Omit or pass an empty array to get a single aggregate result across all methodologies.
Exemple d'appel{"name": "get_hospital_chargemaster_cost", "arguments": {"code": "texte", "code_type": "texte", "hospital_id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"found": true, "results": [], "hospital": "texte", "hospital_id": "texte"}} - list_code_types≈ 274 tokens
Returns every distinct code_type (e.g. CPT, MS-DRG) with catalogued cost data, along with each type's distinct code count and total hospital reports. Unpaginated. Use this to discover which code systems have data before drilling into list_codes.
Paramètres, retour & exemple (0)
Exemple d'appel{"name": "list_code_types", "arguments": {}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"code_types": []}} - list_codes≈ 1290 tokens
Returns every distinct code catalogued under a given code_type, paginated, with each code's raw chargemaster description and the number of hospitals reporting it. Use this to discover which codes exist under a code system (e.g. all CPT codes) before looking up prices with get_hospital_chargemaster_cost or list_hospital_code_costs. Pass query to text-search codes/descriptions instead of listing a whole code_type. Pass hospital_id to restrict results to codes that one hospital actually reports.
Paramètres, retour & exemple (6)
Paramètressort· string · optionnel · CODE_SORT_UNSPECIFIED | CODE_SORT_HOSPITAL_COUNT_DESC | CODE_SORT_SAMPLE_COUNT_DESC | CODE_SORT_CODE_DESC | CODE_SORT_RELEVANCE
Ordering for the returned codes. CODE_SORT_UNSPECIFIED (default) sorts code-alphabetical. CODE_SORT_HOSPITAL_COUNT_DESC sorts most-hospitals-reporting first, for pre-sorted 'top codes' pages. CODE_SORT_SAMPLE_COUNT_DESC sorts by largest network-wide pricing sample size first (sample_count_max, always network-wide regardless of hospital_id) - ranks by how many billing records actually back a code's pricing, rather than by how many hospitals merely report it. CODE_SORT_CODE_DESC is code-alphabetical, reverse order. CODE_SORT_RELEVANCE ranks best text match first (exact code, then code prefix, then description word-start, then description substring), ties broken by network-wide sample count descending, and is only meaningful - and the default - when query is set; without a query it behaves like CODE_SORT_SAMPLE_COUNT_DESC.query· string · optionnel
Case-insensitive text search: matches the code as a prefix, and substrings of the raw and AI-generated descriptions. Descriptions are only searched for queries of 4+ characters; shorter queries match the code prefix only. When set, code_type may be left empty to search across code types.code_type· string · optionnel
Code system to list codes for, e.g. "CPT". From list_code_types. May be left empty when query is set, to search across code types (excluding hospital-specific CDM and LOCAL codes) - CodeSummary.code_type tells the hits apart in that case.page_size· integer · optionnel
Maximum number of results to return. Defaults to 500, capped at 500.page_token· string · optionnel
Opaque token from a previous list_codes response. Omit for the first page. Only valid with the same query/code_type/sort it was issued for.hospital_id· string · optionnel
Optional hospital scoping (a hospital_id from list_hospitals): restricts results to codes that hospital actually reports on its latest revision, and makes sample_count_min/max/exact that hospital's own sample size for the code rather than the network-wide total. Unset (default) is network-wide. page_token is only valid with the same hospital_id it was issued for, same as query/code_type/sort.
Exemple d'appel{"name": "list_codes", "arguments": {"sort": "CODE_SORT_UNSPECIFIED", "query": "texte", "code_type": "texte", "page_size": 1, "page_token": "texte", "hospital_id": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"codes": [], "total_count": 1, "next_page_token": "texte"}} - list_hospital_code_costs≈ 1350 tokens
Returns cost stats for every hospital with a matching chargemaster entry for a code_type/code. Use this instead of calling get_hospital_chargemaster_cost once per hospital when comparing prices for the same procedure across hospitals (e.g. "which hospital has the cheapest MS-DRG 652?"). Defaults to returning every matching hospital (currently at most a few hundred) in one call. If the response's next_page_token is non-empty, the result set was truncated: call this tool again passing that exact value as page_token to get the next page, and keep doing so until next_page_token is empty - do not stop after one page and conclude a hospital has no data for this code. The response's total_count field (total across all pages) can be compared against how many results you've accumulated so far as a completeness check.
Paramètres, retour & exemple (6)
Paramètrescode· string · requiscode_type· string · requis
Code system the chargemaster/billing code belongs to, e.g. APR-DRG, CDM, CPT, HCPCS, MS-DRG, RC. Hospitals may also support additional proprietary code types not listed here.page_size· integer · optionnel
Maximum number of results to return. Defaults to 500 (covering every matching hospital in one call at the current registry size), capped at 500.page_token· string · optionnel
Opaque token from a previous list_hospital_code_costs response's next_page_token field. Omit for the first page. Only valid with the same code_type/code/methodology/min_sample_count it was issued for.methodology· string · optionnel · case rate | fee schedule | other | percent of total billed charges | per diem
Pricing methodology. Omit to aggregate across all methodologies.min_sample_count· integer · optionnel
Minimum pricing sample size: only return hospitals whose price is backed by at least this many billing records (compared against the de-identified range's lower bound, so a '1 through 10' row counts as 1). 0 (default) disables the filter. Pass 1 to exclude hospitals with no real sample data at all (most filings report 0/0, indistinguishable from a genuine zero). total_count and next_page_token describe the filtered set. Negative values are rejected.
Exemple d'appel{"name": "list_hospital_code_costs", "arguments": {"code": "texte", "code_type": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": [], "total_count": 1, "next_page_token": "texte"}} - list_hospitals≈ 1116 tokens
Returns the hospitals supported by the medprice.ai API, with their hospital_id (opaque handle), EIN, name, structured_locations (addresses with geocoded coordinates where available), last_updated_on, and revision history (with per-revision has_payer_data, revision_id, and added_at - when medprice itself ingested that revision, as opposed to revision_date's source-file-reported update date). Defaults to returning the entire registry (currently a few hundred hospitals) in one call. If the response's next_page_token is non-empty, the result set was truncated: call this tool again passing that exact value as page_token to get the next page, and keep doing so until next_page_token is empty - do not stop after one page and conclude the list is complete. The response's total_count field (total across all pages) can be compared against how many hospitals you've accumulated so far as a completeness check, e.g. before answering questions like 'does medprice.ai cover any hospitals in Iowa'.
Paramètres, retour & exemple (2)
Paramètrespage_size· integer · optionnel
Maximum number of hospitals to return. Defaults to 500 (covering the entire current registry in one call), capped at 500.page_token· string · optionnel
Opaque token from a previous list_hospitals response's next_page_token field. Omit for the first page. Do not pass any other value (e.g. an offset or cursor you construct yourself) here.
Exemple d'appel{"name": "list_hospitals", "arguments": {"page_size": 1, "page_token": "texte"}}Exemple de retour{"content": [{"type": "text", "text": "…"}], "structuredContent": {"hospitals": [], "total_count": 1, "next_page_token": "texte"}}
C'est votre serveur ?
Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».