ARS Medica Tech
This is a broad purpose web application for various kinds of clinical use cases. It has a Flask server, a React front end, SurrealDB for a multimodel database, LLM integration, MCP, RAG, OSCAR EMR integration, and much, much more.
What is ARS Medica Tech?
ARS Medica Tech is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this is a broad purpose web application for various kinds of clinical use cases. it has a flask server, a react front end, surrealdb for a multimodel database, llm integration, mcp, rag, oscar emr int...
This is a broad purpose web application for various kinds of clinical use cases. It has a Flask server, a React front end, SurrealDB for a multimodel database, LLM integration, MCP, RAG, OSCAR EMR integration, and much, much more.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- This is a broad purpose web application for various kinds of
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx arsmedicatechConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ARS Medica Tech
ArsMedicaTech is an open-source, integrated clinical platform that combines a Flask REST API backend, React frontend, SurrealDB multi-model database, and LLM integration to support a wide range of healthcare workflows. It includes OSCAR EMR integration via a Dockerized instance, a graph schema for symptoms, diagnoses, treatments and medications, full-text search on encounter histories, and MCP/RAG capabilities for AI-assisted clinical decision support. The project is in active early development under AGPL-3.0 and is intended as a developer-friendly testbed for clinical informatics experimentation.
Prerequisites
- Docker and Docker Compose (the entire stack — Flask, React, Nginx, SurrealDB, OSCAR EMR — runs in containers)
- Python 3.x for local backend development outside Docker
- Node.js and npm for local frontend (React) development
- An OpenAI-compatible LLM API key for the AI/LLM integration features
- An MCP client such as Claude Desktop or Claude Code for MCP-based interactions
Clone the repository
Clone the ArsMedicaTech repository and navigate into it. The full stack is Dockerized so Docker is the primary way to run all components together.
git clone https://github.com/ArsMedicaTech/arsmedicatech
cd arsmedicatechRead the local setup documentation
Review the RUNNING_LOCALLY.md file in the docs/source directory for environment-specific setup steps including Docker Compose configuration and environment variable requirements.
cat docs/source/RUNNING_LOCALLY.mdConfigure environment variables
Create a .env file or export the required environment variables including your LLM API key and database credentials. The app uses SurrealDB and an OpenAI-compatible LLM endpoint.
# Example environment variables (check RUNNING_LOCALLY.md for full list)
export LLM_API_KEY=your_openai_compatible_key
export SURREALDB_URL=http://localhost:8000
export SURREALDB_USER=root
export SURREALDB_PASS=rootStart the Dockerized stack
Use Docker Compose to bring up all services: the Flask API, React app, Nginx reverse proxy, SurrealDB instance, and OSCAR EMR (MariaDB + Tomcat).
docker compose up --buildAccess the application
Once all containers are running, access the React frontend through Nginx. The Flask API is proxied through Nginx as well. Check docker-compose logs if any service fails to start.
# Frontend (via Nginx)
open http://localhost:80
# Check service status
docker compose ps
docker compose logs flask-apiConfigure MCP integration
The platform includes MCP server capabilities for AI agent integration. Configure your MCP client to connect to the Flask API endpoint that exposes MCP tools for clinical data queries.
{
"mcpServers": {
"arsmedicatech": {
"command": "python",
"args": ["-m", "mcp_server"],
"cwd": "/path/to/arsmedicatech",
"env": {
"LLM_API_KEY": "your_key_here"
}
}
}
}ARS Medica Tech Examples
Client configuration
ArsMedicaTech's MCP server runs as part of the Flask backend. Connect your MCP client to the local server process after starting the Docker stack.
{
"mcpServers": {
"arsmedicatech": {
"command": "python",
"args": ["-m", "mcp_server"],
"cwd": "/path/to/arsmedicatech",
"env": {
"LLM_API_KEY": "your_openai_compatible_api_key",
"SURREALDB_URL": "http://localhost:8000"
}
}
}
}Prompts to try
Use these prompts with an MCP-connected AI assistant to interact with the clinical platform.
- "Search the patient encounter history for mentions of diabetes treatment"
- "Show me the graph of symptoms related to hypertension in the knowledge base"
- "Query the ICD code for Type 2 diabetes mellitus"
- "Retrieve recent encounters for patient ID 12345 from the OSCAR EMR integration"Troubleshooting ARS Medica Tech
Docker Compose fails to start the OSCAR EMR container
The OSCAR EMR stack (MariaDB + Tomcat) can take several minutes to initialize on first run. Check logs with `docker compose logs oscar-emr`. Ensure ports 8080 (Tomcat) and 3306 (MariaDB) are not in use by other services.
SurrealDB connection errors from the Flask API
Verify the SurrealDB container is healthy with `docker compose ps`. Ensure SURREALDB_URL, SURREALDB_USER, and SURREALDB_PASS environment variables match the values in your docker-compose.yml. The default credentials are root/root.
Frontend shows blank data — all tables empty
The project currently has hardcoded test data in some endpoints (noted in the roadmap as AMT-016). Live SurrealDB-backed endpoints are being added. Check the GitHub Issues for the current state of data wiring and use the Discussions section to ask about which features have live data.
Frequently Asked Questions about ARS Medica Tech
What is ARS Medica Tech?
ARS Medica Tech is a Model Context Protocol (MCP) server that this is a broad purpose web application for various kinds of clinical use cases. it has a flask server, a react front end, surrealdb for a multimodel database, llm integration, mcp, rag, oscar emr integration, and much, much more. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ARS Medica Tech?
Follow the installation instructions on the ARS Medica Tech GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ARS Medica Tech?
ARS Medica Tech works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ARS Medica Tech free to use?
Yes, ARS Medica Tech is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
ARS Medica Tech Alternatives — Similar Business Applications Servers
Looking for alternatives to ARS Medica Tech? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA 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
★ 46.4kAI 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
★ 44.7kCowAgent (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
★ 39.2kPlatform 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
★ 32.8kAI 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.
Set Up ARS Medica Tech in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ARS Medica Tech?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.