openehr_mcp
Verified Safeby Ayush9284
Overview
Acts as an intelligent bridge, enabling AI assistants to interact seamlessly with openEHR-compliant Electronic Health Record (EHR) systems for natural language access to healthcare data, and provides AI-powered medical coding suggestions.
Installation
python src/openehr_mcp_server.pyEnvironment Variables
- GEMINI_API_KEY
- EHRBASE_URL
- DEFAULT_EHR_ID
- EHRBASE_JSON_FORMAT
- LOG_LEVEL
Security Notes
The project uses environment variables for API keys (e.g., GEMINI_API_KEY) which is good practice. Default credentials (`postgres`/`postgres`, `ehrbase`/`ehrbase`) are hardcoded in `docker-compose.yml` for local development, which is a critical security risk if used in production or if exposed publicly. The `README.md` explicitly warns against exposing EHRbase or Qdrant ports to the internet without proper security. `subprocess.Popen` is used in test files, but not with user-controlled input, mitigating a common risk. JSON parsing from external input is handled, but no 'eval' or direct arbitrary code execution from user input was identified in the core server logic. Overall, security practices for sensitive information storage are good for development, but the default infrastructure credentials require careful consideration for any deployment beyond local testing.
Similar Servers
fhir-mcp-server
Provides seamless integration with FHIR APIs, acting as a bridge between AI/LLM tools and healthcare data for search, retrieval, and analysis.
hm_editor
Electronic Medical Record (EMR) Editor backend with AI integration for structured data management, document generation, and chart visualization.
pyomop
pyomop is a Python library and CLI tool for interacting with OHDSI OMOP Common Data Model (CDM) databases, supporting data loading, vocabulary management, and LLM-based natural language queries through an MCP server.
omcp
OMCP allows AI models to query and analyze healthcare data stored in the OMOP Common Data Model through a standardized, secure interface.