About hl7-fhir-bridge-mcp
hl7-fhir-bridge-mcp is an MCP server that bridges legacy HL7 v2 messages and FHIR for healthcare data workflows. It parses and maps messages, validates FHIR resources, and flags PHI-related compliance risks.
Key features
- 01Parse HL7 v2 messages
- 02Map HL7 v2 to FHIR R4 Bundles
- 03Validate FHIR resource structure
- 04Detect PHI and surface compliance risks
- 05Provide data-minimization advice
Use cases
- 01Convert legacy HL7 v2 messages to FHIR
- 02Check FHIR resources for basic validity
- 03Review clinical messages for PHI risks
MCP support
Exposes HL7/FHIR parsing, mapping, validation, and PHI governance tools to MCP clients. PHI governance can surface HIPAA, MDR, and GDPR Article 9 risks.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEHL7 / FHIR Bridge MCP
mcp-name: io.github.CSOAI-ORG/hl7-fhir-bridge-mcp
Part of the CSOAI Layer-0 legacy-bridge family (sibling of cobol-bridge-mcp). Bridges healthcare legacy messaging (HL7 v2 pipe-delimited) and modern FHIR to ONE OS / CSOAI, and governs PHI.
Tools
parse_hl7v2(message)— message type + key patient fields from a pipe-delimited HL7 v2 message.hl7_to_fhir(message)— map HL7 v2 → a minimal FHIR R4 message Bundle (Patient + MessageHeader).validate_fhir(resource_json)— well-formed JSON + resourceType + basic shape.govern_phi(message_or_fhir)— detect PHI, surface HIPAA/MDR/GDPR-Art.9 risk + data-minimisation advice; attestable on the CSOAI ledger.
Run
pip install -e .
python server.py # stdio MCP server
The win: legacy HL7 / FHIR clinical data → CSOAI PHI governance/attestation → ONE OS. Pairs with hipaa-compliance-mcp + healthcare-ai-governance-mcp + eu-ai-act-compliance-mcp (Annex I medical devices).
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.