Atrium
A reference Model Context Protocol server for SMART-on-FHIR healthcare data — the plumbing every clinical AI team is currently rebuilding.
The Problem
Every healthcare AI team rebuilds the same plumbing between FHIR resources and language models. There is no canonical, production-grade Model Context Protocol server for clinical data. Hospitals that want to adopt MCP-enabled agents will either build it themselves or pay a vendor — and neither path serves the field.
What You'll Build
A reference MCP server, written in TypeScript, that exposes a SMART-on-FHIR sandbox as MCP tools and resources. The first release covers seven resource types — Patient, Observation, Condition, MedicationRequest, Encounter, DiagnosticReport, AllergyIntolerance — with paginated queries, code-system search, and longitudinal slicing. Authentication via SMART OAuth. Full audit logging for HIPAA defensibility. A synthea-seed companion script ships a realistic synthetic patient cohort so any developer can try it in under five minutes.
- 01Model Context Protocol Specification (2025-11-25). Anthropic & MCP Steering Committee, 2025.modelcontextprotocol.io/specification/2025-11-25The authoritative protocol spec Atrium must conform to — tools, resources, transports, JSON-RPC schema.
- 02SMART on FHIR: a standards-based, interoperable apps platform for electronic health records. Mandel et al., JAMIA, 2016.doi.org/10.1093/jamia/ocv189Defines the SMART-on-FHIR OAuth/launch flow Atrium implements for clinical-data authorization.
- 03HL7 FHIR: An Agile and RESTful approach to healthcare information exchange. Bender & Sartipi, IEEE CBMS, 2013.ieeexplore.ieee.org/document/6627810Foundational description of FHIR's REST/resource model underlying every R4 resource type Atrium exposes.
- 04Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic EHR. Walonoski et al., JAMIA, 2018.doi.org/10.1093/jamia/ocx079Source of the synthetic FHIR patients Atrium uses for seeding and integration tests.
- 05Toolformer: Language Models Can Teach Themselves to Use Tools. Schick et al., NeurIPS, 2023.arxiv.org/abs/2302.04761Canonical reference for LLM tool-use that motivates exposing FHIR operations as discrete MCP tools.
- 06ReAct: Synergizing Reasoning and Acting in Language Models. Yao et al., ICLR, 2023.arxiv.org/abs/2210.03629Reasoning-plus-acting loop pattern that frontier LLMs use when chaining Atrium's MCP tool calls against patient data.
- 07Gorilla: Large Language Model Connected with Massive APIs. Patil et al., NeurIPS, 2024.arxiv.org/abs/2305.15334Tool retrieval and accurate API-call generation — directly relevant to scaling Atrium's tool surface without hallucinated FHIR queries.
- 08Large language models encode clinical knowledge (Med-PaLM). Singhal et al., Nature, 2023.doi.org/10.1038/s41586-023-06291-2Establishes the frontier-LLM clinical competence Atrium is designed to serve with grounded FHIR context.
- 09Enhancing Clinical Decision Support and EHR Insights through LLMs and the Model Context Protocol: An Open-Source MCP-FHIR Framework. Ehtesham et al., 2025.arxiv.org/abs/2506.13800Closest prior art: an MCP-FHIR bridge evaluated on a SMART Health IT sandbox; Atrium positions against and extends this.
- 10Testing and Evaluation of Health Care Applications of Large Language Models: A Systematic Review. Bedi et al., JAMA, 2025.jamanetwork.com/journals/jama/fullarticle/2825147Defines the evaluation gaps (real patient data, admin tasks, fairness) Atrium's own eval harness must target.