Taiwan Health

v1.0.0Business Applicationsstable

MCP server for taiwan health mcp

healthllmmcpmcp-toolstaiwan
Share:
150
Stars
0
Downloads
0
Weekly
0/5

What is Taiwan Health?

Taiwan Health is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for taiwan health mcp

MCP server for taiwan health mcp

This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server for taiwan health mcp

Use Cases

Access Taiwan health and medical data
Query health information via MCP tools
LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 18, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx taiwan-health-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Taiwan Health

Taiwan Health MCP is a self-hosted Python MCP server that exposes approximately 51 medical and health-data tools covering ICD-10 codes, TFDA drug information, LOINC laboratory tests, SNOMED CT clinical terminology, clinical guidelines, FHIR IG profiles, food nutrition data, and health supplements for the Taiwan healthcare ecosystem. It runs as a Docker stack with PostgreSQL (pgvector), Redis, and MinIO, and serves AI clients either via native MCP (streamable-HTTP) or an OpenAPI bridge. Clinicians, developers, and researchers working with Taiwanese health standards use it to query, cross-reference, and validate medical data without calling external APIs.

Prerequisites

  • Docker and Docker Compose installed on the host machine
  • Python 3.12+ available if running without Docker
  • PostgreSQL 16 with the pgvector extension (provided automatically via Docker Compose)
  • Ollama with qwen3-embedding model installed if you want semantic (vector) search (keyword fallback is available without it)
  • An MCP-compatible client such as Claude Desktop (v0.6.31+) or Open WebUI
1

Clone the repository

Clone the Taiwan Health MCP repository to your server or development machine.

git clone https://github.com/healthymind-tech/Taiwan-Health-MCP.git
cd Taiwan-Health-MCP
2

Configure environment variables

Copy the example .env file and fill in the required values including database password, admin credentials, and session secret.

cp .env.example .env
# Edit .env and set at minimum:
# POSTGRES_PASSWORD=<strong-password>
# ADMIN_ENABLED=true
# ADMIN_USERNAME=admin
# ADMIN_PASSWORD_HASH=sha256$<hash>
# ADMIN_SESSION_SECRET=<random-32-char-string>

# Generate a password hash:
python -c "import hashlib; print('sha256$' + hashlib.sha256(b'your-password').hexdigest())"
3

Start the Docker stack

Launch all services (MCP server, PostgreSQL, Redis, MinIO) using Docker Compose.

docker compose up -d
4

Import medical data via the Admin Console

Navigate to http://localhost:8000/admin and use the Tasks tab to import ICD-10-CM/PCS, LOINC, SNOMED CT, TFDA drugs, and food nutrition data. Embeddings for semantic search are generated automatically after import.

5

Connect your MCP client to the server

Point your MCP client at the streamable-HTTP endpoint. For Claude Desktop, add the server configuration shown below.

{
  "mcpServers": {
    "taiwan-health": {
      "type": "http",
      "url": "http://localhost:8000/mcp"
    }
  }
}

Taiwan Health Examples

Client configuration (HTTP transport)

Claude Desktop configuration connecting to a locally running Taiwan Health MCP instance via streamable HTTP.

{
  "mcpServers": {
    "taiwan-health": {
      "type": "http",
      "url": "http://localhost:8000/mcp"
    }
  }
}

Prompts to try

Natural-language queries that map to the server's 51 exposed tools across ICD-10, drugs, LOINC, nutrition, and FHIR.

- "What is the ICD-10 code for type 2 diabetes with kidney complications?"
- "Look up the TFDA-registered drug details for Aspirin 100mg"
- "Search LOINC codes related to HbA1c blood tests"
- "What are the clinical guidelines for managing hypertension in Taiwan?"
- "Analyse the nutritional content of a meal: 100g white rice, 150g grilled salmon, 80g broccoli"
- "Find SNOMED CT concepts related to myocardial infarction"

Troubleshooting Taiwan Health

Tools show as disabled or return empty results after startup

Tools auto-enable only after their data module has been imported. Go to the Admin Console at /admin and check the Tasks tab to import the required dataset (e.g. ICD-10, LOINC, TFDA drugs). Tools will become active once the import completes.

Semantic search returns no results even after import

Semantic search requires Ollama with the qwen3-embedding model running and accessible. If Ollama is not configured, the server falls back to keyword search automatically. Check your Ollama endpoint configuration in .env.

Admin Console login fails with password hash error

Generate the hash correctly using: python -c "import hashlib; print('sha256$' + hashlib.sha256(b'your-password').hexdigest())" and paste the full output (including the sha256$ prefix) into ADMIN_PASSWORD_HASH in .env, then restart the containers.

Frequently Asked Questions about Taiwan Health

What is Taiwan Health?

Taiwan Health is a Model Context Protocol (MCP) server that mcp server for taiwan health mcp It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Taiwan Health?

Follow the installation instructions on the Taiwan Health GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Taiwan Health?

Taiwan Health works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Taiwan Health free to use?

Yes, Taiwan Health is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Taiwan Health Alternatives — Similar Business Applications Servers

Looking for alternatives to Taiwan Health? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.

n8n

189.1k

A comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou

LobeHub

77.5k

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Jeecgboot

46.4k

AI 低代码平台,「低代码 + 零代码」双模式驱动:低代码一键生成前后端代码,零代码 5 分钟搭建系统,AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等,兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式,消除 Java 项目 80% 的重复工作,提效而不失灵活。

CowAgent

44.7k

CowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入,可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助理和企业数字员工。

Minds Platform

39.2k

Platform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.

Astrbot

32.8k

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

Browse More Business Applications MCP Servers

Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "taiwan-health-mcp": { "command": "npx", "args": ["-y", "taiwan-health-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Taiwan Health?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides