Mcp Clinical Reasoner

io.github.pcmedsinge由 GitHub 帳號 pcmedsinge 發布v1.0.0更新於 Oct 24, 2026

Drug interactions (FDA), dose range check, allergy cross-reactivity. No PHI processed.

發布方自己的服務：[PREPROD] Clinical.ly Research Suite

已驗證STDIO僅桌面知識與記憶 AI 與機器學習

服務詳細資訊

識別碼: io.github.pcmedsinge/mcp-clinical-reasoner
傳輸: STDIO
執行環境: Desktop only
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此條目所屬的 GitHub 帳號 pcmedsinge。這並不表明該帳號就是產品方。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.pcmedsinge%2Fmcp-clinical-reasoner.svg)](https://sourceweft.com/mcp/io.github.pcmedsinge%2Fmcp-clinical-reasoner?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

本機 MCP 伺服器，為助理提供四項臨床藥理工具：藥品查詢、藥物交互作用檢查、劑量範圍檢查與過敏交叉反應檢查。

可以做什麼: 依藥品名稱或 RxNorm CUI 查詢藥品，經 NLM RxNav API 回傳標準名稱、RxCUI、藥物類別與劑量參考，並自動解析品牌別名（例如 Tylenol 對應 acetaminophen）。透過同一 API 檢查 2 至 10 個 RxNorm CUI 之間的藥物交互作用，並依嚴重程度排序。依內建約 20 種常用藥品的劑量表，驗證擬用的單次劑量（毫克）。依內建的 12 個過敏原類別（例如青黴素、磺胺類、NSAID）檢查過敏交叉反應。
適用情境: 適合研究、教學或原型開發情境，讓助理快速參考藥品名稱、交互作用、成人劑量範圍或過敏交叉反應。不能取代臨床判斷、藥師審核或專業醫療建議。
執行需求: 以本機 Python 程序執行，透過 uv 從 PyPI 套件安裝；預設使用 stdio 傳輸，也可選用 8002 埠的 SSE 模式。藥品查詢與交互作用檢查需要連線至 RxNav REST API 的網路存取，無需 API 金鑰。選用環境變數可設定 RxNav 基礎位址與逾時、傳輸方式、主機、埠、日誌等級以及 LangFuse 追蹤金鑰。

安裝前請注意

劑量上限與交叉反應規則來自一般成人參考資料，須依每位病人個別調整；README 聲明此伺服器僅供研究與教學用途，不能取代臨床判斷或藥師審核。藥品查詢與交互作用請求會傳送至第三方 NLM RxNav API。若透過 LANGFUSE_PUBLIC_KEY 與 LANGFUSE_SECRET_KEY 啟用 LangFuse 追蹤，工具呼叫會記錄延遲與回應大小。README 聲明不處理 PHI。

安裝

在 SourceWeft 中

開啟儀表板中的 Mcp Clinical Reasoner，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照儲存庫中的啟動說明。

README

mcp-clinical-reasoner

Part of fhir-mcp-suite — v1.0.0

An MCP server providing four clinical pharmacology tools backed by the free NLM RxNav REST API and a built-in rule-based reference table. No API key required. No PHI processed.

[License]

Tools

Tool	Transport	Description
`lookup_drug`	RxNav API	Resolve drug name or RxNorm CUI → canonical name, RxCUI, drug-class membership, dose reference
`check_drug_interactions`	RxNav API	Detect drug-drug interactions (DDIs) for 2–10 RxNorm CUIs, sorted by severity
`check_dose`	Rule-based	Validate a proposed single dose (mg) against a built-in table of ~20 common drugs
`check_allergy_conflicts`	Rule-based	Cross-reactivity check against 12 allergen classes using built-in table

Architecture

Claude Desktop / LangGraph agent          │  MCP (stdio or SSE)          ▼ mcp-clinical-reasoner  (:8002 in SSE mode)    ├── lookup_drug ────────────────► rxnav.nlm.nih.gov/REST    ├── check_drug_interactions ────► rxnav.nlm.nih.gov/REST    ├── check_dose ─────────────────► built-in DOSE_TABLE (20 drugs)    └── check_allergy_conflicts ────► built-in ALLERGEN_CLASSES (12 classes)

Claude Desktop / LangGraph agent          │  MCP (stdio or SSE)          ▼ mcp-clinical-reasoner  (:8002 in SSE mode)    ├── lookup_drug ────────────────► rxnav.nlm.nih.gov/REST    ├── check_drug_interactions ────► rxnav.nlm.nih.gov/REST    ├── check_dose ─────────────────► built-in DOSE_TABLE (20 drugs)    └── check_allergy_conflicts ────► built-in ALLERGEN_CLASSES (12 classes)

All tool calls traced via LangFuse (session-scoped, latency + response bytes).

Built-in Dose Table

Covers 20 common drugs: acetaminophen, ibuprofen, aspirin, naproxen, metformin, lisinopril, atorvastatin, metoprolol, amlodipine, omeprazole, amoxicillin, azithromycin, warfarin, furosemide, sertraline, gabapentin, clopidogrel, hydrochlorothiazide, prednisone, albuterol.

Brand aliases are resolved automatically (e.g. "Tylenol" → acetaminophen, "Advil" → ibuprofen).

Built-in Allergen Classes

12 classes: penicillin, cephalosporin, sulfonamide, nsaid, macrolide, fluoroquinolone, statin, ace_inhibitor, angiotensin_receptor_blocker, beta_blocker, thiazide_diuretic, tetracycline.

Quick start

bash

# Install (uv workspace from repo root)uv sync --all-packages
# Run (stdio, default)uv run mcp-clinical-reasoner
# Run (SSE on port 8002)MCP_TRANSPORT=sse uv run mcp-clinical-reasoner

# Install (uv workspace from repo root)uv sync --all-packages
# Run (stdio, default)uv run mcp-clinical-reasoner
# Run (SSE on port 8002)MCP_TRANSPORT=sse uv run mcp-clinical-reasoner

Environment variables

Variable	Default	Description
`RXNAV_BASE_URL`	`https://rxnav.nlm.nih.gov/REST`	RxNav API base URL
`RXNAV_TIMEOUT_S`	`30.0`	HTTP timeout (seconds)
`MCP_TRANSPORT`	`stdio`	`stdio` or `sse`
`MCP_HOST`	`0.0.0.0`	SSE bind host
`MCP_PORT`	`8002`	SSE port
`LANGFUSE_PUBLIC_KEY`	(optional)	LangFuse tracing
`LANGFUSE_SECRET_KEY`	(optional)	LangFuse tracing
`LANGFUSE_HOST`	(optional)	LangFuse host
`LOG_LEVEL`	`INFO`	Logging level

Claude Desktop configuration

json

{  "mcpServers": {    "clinical-reasoner": {      "command": "uv",      "args": [        "--directory", "/path/to/fhir-mcp-suite",        "run", "--package", "mcp-clinical-reasoner",        "mcp-clinical-reasoner"      ]    }  }}

{  "mcpServers": {    "clinical-reasoner": {      "command": "uv",      "args": [        "--directory", "/path/to/fhir-mcp-suite",        "run", "--package", "mcp-clinical-reasoner",        "mcp-clinical-reasoner"      ]    }  }}

Tests

bash

# Unit tests (36 tests, no network required)uv run pytest packages/mcp-clinical-reasoner/tests/ -v -m "not integration and not eval"
# Offline eval (dose + allergy + error validation)uv run python evals/mcp-clinical-reasoner/run_eval.py --tags dose allergy error
# Full eval suite (requires rxnav.nlm.nih.gov)uv run python evals/mcp-clinical-reasoner/run_eval.py

# Unit tests (36 tests, no network required)uv run pytest packages/mcp-clinical-reasoner/tests/ -v -m "not integration and not eval"
# Offline eval (dose + allergy + error validation)uv run python evals/mcp-clinical-reasoner/run_eval.py --tags dose allergy error
# Full eval suite (requires rxnav.nlm.nih.gov)uv run python evals/mcp-clinical-reasoner/run_eval.py

Eval results (offline, no network)

Disclaimer

This server is for research and educational purposes only. It does not replace clinical judgement, pharmacist review, or professional medical advice. All dose limits and cross-reactivity rules are from general adult references and must be individualised for each patient.