mcp-fhir-patient-index
by Shaumik-Ashraf
Overview
A Ruby on Rails Master Patient Index (MPI) server with a user-friendly UI, a conformant FHIR API (R4), and Model Context Protocol (MCP) support for LLM integration, focused on managing patient demographic data.
Installation
rails serverEnvironment Variables
- RAILS_MASTER_KEY
- RAILS_MAX_THREADS
- PORT
- PIDFILE
- SOLID_QUEUE_IN_PUMA
- RAILS_LOG_LEVEL
- JOB_CONCURRENCY
- WEB_CONCURRENCY
- DB_HOST
- KAMAL_REGISTRY_PASSWORD
Security Notes
The README explicitly warns that the application is 'not ready for real-patient data out of the box' and requires credential regeneration and SOC-II compliance for real-world use. It implements basic Rails security features like strong parameters and filtering sensitive logs (e.g., SSN). The `format_ssn` helper masks SSN in the UI based on a setting, but the raw data is stored. CSRF protection is skipped for the MCP API endpoint, which is common for API-only controllers. There are no obvious hardcoded secrets directly in the repository for critical configurations (it uses Rails credentials and environment variables for deployment). No 'eval' or malicious patterns are evident.
Similar Servers
rails-mcp-server
Enables Large Language Models (LLMs) to interact with Rails projects for code analysis, exploration, and development assistance using the Model Context Protocol.
action_mcp
ActionMCP is a Ruby gem providing Model Context Protocol (MCP) server capabilities to Rails applications, enabling AI assistants to connect to external data sources and tools.
fhir-mcp-server
The FHIR MCP Server acts as a bridge between AI/LLM tools and FHIR APIs, enabling seamless search, retrieval, and analysis of clinical information.
pyomop
A Python library providing tools for managing OMOP Common Data Model databases, including LLM-powered natural language querying, FHIR-to-OMOP data conversion, and PyHealth/PLP compatibility for machine learning pipelines.