Skip to content
Back to search

healthcare-mcp-public

A Model Context Protocol (MCP) server providing AI assistants with access to healthcare data and medical information tools, including FDA drug info, PubMed, medRxiv, NCBI Bookshelf, clinical trials, ICD-10, DICOM metadata, and a medical calculator.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/cicatriiz--healthcare-mcp-public/badge.svg)](/listings/cicatriiz--healthcare-mcp-public)

HTML

<a href="/listings/cicatriiz--healthcare-mcp-public"><img src="/api/listings/cicatriiz--healthcare-mcp-public/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Option 1: DXT Extension (Recommended)

1. Download `healthcare-mcp.dxt` from this repository 2. Open with your compatible MCP client (such as Claude Desktop) 3. Follow the installation prompts 4. Configure optional settings through the GUI

Option 2: Installing via Smithery

To install Healthcare Data and Medical Information Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@Cicatriiz/healthcare-mcp-public):

npx -y @smithery/cli install @Cicatriiz/healthcare-mcp-public --client claude

Option 3: npm Installation

1. Install the package:

   npm install healthcare-mcp

2. Run the server:

   npx healthcare-mcp

Option 4: Manual Installation from Source

1. Clone the repository:

   git clone https://github.com/Cicatriiz/healthcare-mcp-public.git
   cd healthcare-mcp-public/server

2. Install dependencies:

   npm install

3. Set up environment variables (optional):

   # Create .env file from example
   cp .env.example .env
   # Edit .env with your API keys (optional)

4. Run the server:

   npm start

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 433 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Healthcare MCP Server
  2. [![smithery badge](https://smithery.ai/badge/@Cicatriiz/healthcare-mcp-public)](https://smithery.ai/server/@Cicatriiz/healthcare-mcp-public)
  3. A Model Context Protocol (MCP) server providing AI assistants with access to healthcare data and medical information tools.
  4. ## Overview
  5. Healthcare MCP Server is a specialized Node.js server that implements the Model Context Protocol (MCP) to provide AI assistants with access to healthcare data and medical information tools. It enables AI models to retrieve accurate, up-to-date medical information from authoritative sources. This repository provides a single DXT package containing the complete Node.js implementation.
  6. ## DXT Extension
  7. This repository includes a packaged DXT (Desktop Extension) file for easy installation in compatible development environments. Download `healthcare-mcp.dxt` for one-click installation.
  8. ## Features
  9. - **FDA Drug Information**: Search and retrieve comprehensive drug information from the FDA database (improved response parsing)
  10. - **PubMed Research**: Search medical literature from PubMed's database of scientific articles
  11. - **Health Topics**: Access evidence-based health information from Health.gov (updated to API v4)
  12. - **Clinical Trials**: Search for ongoing and completed clinical trials (updated API parameters)
  13. - **Medical Terminology**: Look up ICD-10 codes and medical terminology definitions
  14. - **medRxiv Search**: Search for pre-print articles on medRxiv
  15. - **Medical Calculator**: Calculate Body Mass Index (BMI)
  16. - **NCBI Bookshelf Search**: Search the NCBI Bookshelf for biomedical books and documents
  17. - **DICOM Metadata Extraction**: Extract metadata from a DICOM file
  18. - **Caching**: Efficient caching system with connection pooling to reduce API calls and improve performance
  19. - **Usage Tracking**: Anonymous usage tracking to monitor API usage
  20. - **Error Handling**: Robust error handling and logging
  21. - **Multiple Interfaces**: Support for both stdio (for CLI) and HTTP/SSE interfaces
  22. - **API Documentation**: Interactive API documentation with Swagger UI
  23. - **Comprehensive Testing**: Extensive test suite with Node.js testing and API verification
  24. ## Installation
  25. ### Option 1: DXT Extension (Recommended)
  26. 1. Download `healthcare-mcp.dxt` from this repository
  27. 2. Open with your compatible MCP client (such as Claude Desktop)
  28. 3. Follow the installation prompts
  29. 4. Configure optional settings through the GUI
  30. ### Option 2: Installing via Smithery
  31. To install Healthcare Data and Medical Information Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@Cicatriiz/healthcare-mcp-public):
  32. ```bash
  33. npx -y @smithery/cli install @Cicatriiz/healthcare-mcp-public --client claude
  34. ```
  35. ### Option 3: npm Installation
  36. 1. Install the package:
  37. ```bash
  38. npm install healthcare-mcp
  39. ```
  40. 2. Run the server:
  41. ```bash
  42. npx healthcare-mcp
  43. ```
  44. ### Option 4: Manual Installation from Source
  45. 1. Clone the repository:
  46. ```bash
  47. git clone https://github.com/Cicatriiz/healthcare-mcp-public.git
  48. cd healthcare-mcp-public/server
  49. ```
  50. 2. Install dependencies:
  51. ```bash
  52. npm install
  53. ```
  54. 3. Set up environment variables (optional):
  55. ```bash
  56. # Create .env file from example
  57. cp .env.example .env
  58. # Edit .env with your API keys (optional)
  59. ```
  60. 4. Run the server:
  61. ```bash
  62. npm start
  63. ```
  64. ## Usage
  65. ### Running the Server
  66. - **stdio mode** (default, for MCP clients):
  67. ```bash
  68. npm start
  69. ```
  70. - **HTTP/SSE mode** (for web clients):
  71. ```bash
  72. npm run server:http
  73. ```
  74. ### Testing the Tools
  75. You can test the MCP tools using the built-in test scripts:
  76. ```bash
  77. # Test all tools
  78. npm test
  79. # Test individual tools
  80. npm run test:fda # Test FDA drug lookup
  81. npm run test:pubmed # Test PubMed search
  82. npm run test:health # Test Health Topics
  83. npm run test:trials # Test Clinical Trials search
  84. npm run test:icd # Test ICD-10 code lookup
  85. ```
  86. ## API Reference
  87. The Healthcare MCP Server provides both a programmatic API for direct integration and a RESTful HTTP API for web clients.
  88. ### RESTful API Endpoints
  89. When running in HTTP mode, the following endpoints are available:
  90. #### Health Check
  91. ```
  92. GET /health
  93. ```
  94. Returns the status of the server and its services.
  95. #### FDA Drug Lookup
  96. ```
  97. GET /api/fda?drug_name={drug_name}&search_type={search_type}
  98. ```
  99. **Parameters:**
  100. - `drug_name`: Name of the drug to search for
  101. - `search_type`: Type of information to retrieve
  102. - `general`: Basic drug information (default)
  103. - `label`: Drug labeling information
  104. - `adverse_events`: Reported adverse events
  105. **Example Response:**
  106. ```json
  107. {
  108. "status": "success",
  109. "drug_name": "aspirin",
  110. "search_type": "general",
  111. "total_results": 25,
  112. "results": [
  113. {
  114. "brand_name": "ASPIRIN",
  115. "generic_name": "ASPIRIN",
  116. "manufacturer": "Bayer Healthcare",
  117. "product_type": "HUMAN OTC DRUG",
  118. "route": "ORAL",
  119. "active_ingredients": [
  120. {
  121. "name": "ASPIRIN",
  122. "strength": "325 mg/1"
  123. }
  124. ]
  125. }
  126. ]
  127. }
  128. ```
  129. #### PubMed Search
  130. ```
  131. GET /api/pubmed?query={query}&max_results={max_results}&date_range={date_range}
  132. ```
  133. **Parameters:**
  134. - `query`: Search query for medical literature
  135. - `max_results`: Maximum number of results to return (default: 5, max: 50)
  136. - `date_range`: Limit to articles published within years (e.g. '5' for last 5 years)
  137. **Example Response:**
  138. ```json
  139. {
  140. "status": "success",
  141. "query": "diabetes treatment",
  142. "total_results": 123456,
  143. "date_range": "5",
  144. "articles": [
  145. {
  146. "pmid": "12345678",
  147. "title": "New advances in diabetes treatment",
  148. "authors": ["Smith J", "Johnson A"],
  149. "journal": "Journal of Diabetes Research",
  150. "publication_date": "2023-01-15",
  151. "abstract": "This study explores new treatment options...",
  152. "url": "https://pubmed.ncbi.nlm.nih.gov/12345678/"
  153. }
  154. ]
  155. }
  156. ```
  157. #### Health Topics
  158. ```
  159. GET /api/health_finder?topic={topic}&language={language}
  160. ```
  161. **Parameters:**
  162. - `topic`: Health topic to search for information
  163. - `language`: Language for content (en or es, default: en)
  164. **Example Response:**
  165. ```json
  166. {
  167. "status": "success",
  168. "search_term": "diabetes",
  169. "language": "en",
  170. "total_results": 15,
  171. "topics": [
  172. {
  173. "title": "Diabetes Type 2",
  174. "url": "https://health.gov/myhealthfinder/topics/health-conditions/diabetes/diabetes-type-2",
  175. "last_updated": "2023-05-20",
  176. "section": "Health Conditions",
  177. "description": "Information about managing type 2 diabetes",
  178. "content": ["Diabetes is a disease...", "Treatment options include..."]
  179. }
  180. ]
  181. }
  182. ```
  183. #### Clinical Trials Search
  184. ```
  185. GET /api/clinical_trials?condition={condition}&status={status}&max_results={max_results}
  186. ```
  187. **Parameters:**
  188. - `condition`: Medical condition or disease to search for
  189. - `status`: Trial status (recruiting, completed, active, not_recruiting, or all)
  190. - `max_results`: Maximum number of results to return (default: 10, max: 100)
  191. **Example Response:**
  192. ```json
  193. {
  194. "status": "success",
  195. "condition": "breast cancer",
  196. "search_status": "recruiting",
  197. "total_results": 256,
  198. "trials": [
  199. {
  200. "nct_id": "NCT12345678",
  201. "title": "Study of New Treatment for Breast Cancer",
  202. "status": "Recruiting",
  203. "phase": "Phase 2",
  204. "study_type": "Interventional",
  205. "conditions": ["Breast Cancer", "HER2-positive Breast Cancer"],
  206. "locations": [
  207. {
  208. "facility": "Memorial Hospital",
  209. "city": "New York",
  210. "state": "NY",
  211. "country": "United States"
  212. }
  213. ],
  214. "sponsor": "National Cancer Institute",
  215. "url": "https://clinicaltrials.gov/study/NCT12345678",
  216. "eligibility": {
  217. "gender": "Female",
  218. "min_age": "18 Years",
  219. "max_age": "75 Years",
  220. "healthy_volunteers": "No"
  221. }
  222. }
  223. ]
  224. }
  225. ```
  226. #### ICD-10 Code Lookup
  227. ```
  228. GET /api/medical_terminology?code={code}&description={description}&max_results={max_results}
  229. ```
  230. **Parameters:**
  231. - `code`: ICD-10 code to look up (optional if description is provided)
  232. - `description`: Medical condition description to search for (optional if code is provided)
  233. - `max_results`: Maximum number of results to return (default: 10, max: 50)
  234. **Example Response:**
  235. ```json
  236. {
  237. "status": "success",
  238. "search_type": "description",
  239. "search_term": "diabetes",
  240. "total_results": 25,
  241. "codes": [
  242. {
  243. "code": "E11",
  244. "description": "Type 2 diabetes mellitus",
  245. "category": "Endocrine, nutritional and metabolic diseases"
  246. },
  247. {
  248. "code": "E10",
  249. "description": "Type 1 diabetes mellitus",
  250. "category": "Endocrine, nutritional and metabolic diseases"
  251. }
  252. ]
  253. }
  254. ```
  255. #### Generic Tool Execution
  256. ```
  257. POST /mcp/call-tool
  258. ```
  259. **Request Body:**
  260. ```json
  261. {
  262. "name": "fda_drug_lookup",
  263. "arguments": {
  264. "drug_name": "aspirin",
  265. "search_type": "general"
  266. },
  267. "session_id": "optional-session-id"
  268. }
  269. ```
  270. ### MCP Tools
  271. When using the MCP server through compatible clients, the following tools are available:
  272. #### FDA Drug Lookup
  273. ```javascript
  274. fda_drug_lookup(drug_name, search_type = "general")
  275. ```
  276. **Parameters:**
  277. - `drug_name`: Name of the drug to search for
  278. - `search_type`: Type of information to retrieve
  279. - `general`: Basic drug information (default)
  280. - `label`: Drug labeling information
  281. - `adverse_events`: Reported adverse events
  282. #### PubMed Search
  283. ```javascript
  284. pubmed_search(query, max_results = 5, date_range = "")
  285. ```
  286. **Parameters:**
  287. - `query`: Search query for medical literature
  288. - `max_results`: Maximum number of results to return (default: 5)
  289. - `date_range`: Limit to articles published within years (e.g. '5' for last 5 years)
  290. #### Health Topics
  291. ```javascript
  292. health_topics(topic, language = "en")
  293. ```
  294. **Parameters:**
  295. - `topic`: Health topic to search for information
  296. - `language`: Language for content (en or es, default: en)
  297. #### Clinical Trials Search
  298. ```javascript
  299. clinical_trials_search(condition, status = "recruiting", max_results = 10)
  300. ```
  301. **Parameters:**
  302. - `condition`: Medical condition or disease to search for
  303. - `status`: Trial status (recruiting, completed, active, not_recruiting, or all)
  304. - `max_results`: Maximum number of results to return
  305. #### ICD-10 Code Lookup
  306. ```javascript
  307. lookup_icd_code(code = null, description = null, max_results = 10)
  308. ```
  309. **Parameters:**
  310. - `code`: ICD-10 code to look up (optional if description is provided)
  311. - `description`: Medical condition description to search for (optional if code is provided)
  312. - `max_results`: Maximum number of results to return
  313. #### medRxiv Search
  314. ```javascript
  315. medrxiv_search(query, max_results = 10)
  316. ```
  317. **Parameters:**
  318. - `query`: Search query for medRxiv articles
  319. - `max_results`: Maximum number of results to return
  320. #### Calculate BMI
  321. ```javascript
  322. calculate_bmi(height_meters, weight_kg)
  323. ```
  324. **Parameters:**
  325. - `height_meters`: Height in meters
  326. - `weight_kg`: Weight in kilograms
  327. #### NCBI Bookshelf Search
  328. ```javascript
  329. ncbi_bookshelf_search(query, max_results = 10)
  330. ```
  331. **Parameters:**
  332. - `query`: Search query for NCBI Bookshelf
  333. - `max_results`: Maximum number of results to return
  334. #### Extract DICOM Metadata
  335. ```javascript
  336. extract_dicom_metadata(file_path)
  337. ```
  338. **Parameters:**
  339. - `file_path`: Path to the DICOM file
  340. ## Data Sources
  341. This MCP server utilizes several publicly available healthcare APIs:
  342. - [FDA OpenFDA API](https://open.fda.gov/apis/)
  343. - [PubMed E-utilities API](https://www.ncbi.nlm.nih.gov/books/NBK25500/)
  344. - [Health.gov API](https://health.gov/our-work/national-health-initiatives/health-literacy/consumer-health-content/free-web-content/apis-developers)
  345. - [ClinicalTrials.gov API](https://clinicaltrials.gov/data-api/about-api)
  346. - [NLM Clinical Table Search Service for ICD-10-CM](https://clinicaltables.nlm.nih.gov/apidoc/icd10cm/v3/doc.html)
  347. ## License
  348. MIT License

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.