DICOM/HL7/FHIR Interoperability MCP Server
This MCP server is a healthcare interoperability toolkit bridging DICOM, HL7v2, and FHIR standards, with optional PACS connectivity.
Free (Reference) Tools
DICOM Tag Lookup/Explanation – Look up any DICOM tag by number or keyword (VR, VM, description, usage, vendor quirks for GE/Siemens/Philips)
HL7 Message Parsing – Parse raw HL7 v2.x pipe-delimited messages into human-readable segments with field names, values, and table lookups
HL7 Segment Explanation – Explain any HL7 segment (e.g., PID, OBX, ORC) with field positions, data types, and optionality
HL7 Table Lookup – Look up HL7 coded table values (e.g., Table 0001 = Administrative Sex)
Premium Mapping & Generation Tools
DICOM → HL7 Mapping – Map DICOM tags to HL7 v2 segment fields with data type conversion notes
HL7 → FHIR Mapping – Map HL7 v2 fields to FHIR R4 resource elements with ConceptMap references
Mirth Connect Channel Generation – Generate complete channel XML with source/destination connectors, transformers, and filters
HL7 Message Validation – Validate HL7 v2.x messages for required fields, data types, table values, and cross-segment consistency
Integration Pattern Explanation – Explain patterns (ADT feed, radiology workflow, order-to-result, patient merge, etc.) with flow diagrams and best practices
Private Tag Decoding – Decode vendor-specific private DICOM tags (Philips, GE, Siemens, Fuji, Agfa, Canon/Toshiba, Hologic)
Sample HL7 Message Generation – Generate realistic sample HL7 messages (ADT, ORM, ORU, MDM, SIU, DFT) for testing
Premium PACS Connectivity Tools
PACS Echo – Verify PACS connectivity via C-ECHO (DIMSE) or HTTP ping (DICOMweb)
PACS Query – Search for studies/series by patient ID, name, accession number, date range, modality, or description via C-FIND or QIDO-RS
PACS Metadata Retrieval – Retrieve detailed DICOM header metadata for a study or series via WADO-RS or C-FIND
PACS Retrieve (C-MOVE) – Initiate C-MOVE to transfer images to a destination AE title (disabled by default, requires explicit opt-in)
PACS Study Summary – Query a study and receive a full interoperability package: PACS metadata + DICOM→HL7 mapping + HL7→FHIR mapping + a pre-filled ORM^O01 message skeleton
PHI Safety Features: Built-in log redaction, result warnings, optional output redaction, and C-MOVE disabled by default.
Enables decoding of Siemens-specific private DICOM tags, supporting specialized medical imaging informatics and interoperability workflows.
Provides support for decoding Toshiba-specific private DICOM tags, ensuring accurate data mapping and integration for healthcare systems using Toshiba equipment.
DICOM/HL7/FHIR Interoperability MCP Server
The only MCP server that bridges DICOM, HL7v2, and FHIR in one package — with optional PACS connectivity.
Built by a healthcare IT engineer with 16 years of PACS, RIS, and integration experience. This isn't a wrapper around a FHIR API or a DICOM tag dictionary — it's the interoperability knowledge that takes years on the job to build, plus the ability to connect to real PACS systems.
What Makes This Different
Capability | This Server | DICOM-only servers | FHIR-only servers |
DICOM tag lookup + vendor quirks | Yes | Yes | No |
HL7v2 message parsing | Yes | No | No |
FHIR R4 resource mapping | Yes | No | Yes |
DICOM ↔ HL7v2 mapping | Yes | No | No |
HL7v2 → FHIR conversion | Yes | No | No |
Mirth Connect channel generation | Yes | No | No |
PACS connectivity (C-FIND/C-MOVE) | Yes | Some | No |
DICOMweb (QIDO-RS/WADO-RS) | Yes | No | No |
Query PACS + auto-map to HL7/FHIR | Yes | No | No |
Vendor private tag decoding (GE, Siemens, Philips) | Yes | Some | No |
Integration pattern knowledge (IHE SWF, ADT flows) | Yes | No | No |
Related MCP server: DICOM API MCP Server
Tools
Reference Tools (Free)
Tool | What It Does |
| Look up any DICOM tag by number or keyword |
| Detailed tag explanation with vendor quirks and gotchas |
| Parse HL7 v2.x messages into human-readable format |
| Explain segment fields, data types, and usage |
| Look up HL7 table values (Administrative Sex, Patient Class, etc.) |
Mapping & Generation Tools (Premium)
Tool | What It Does |
| Map DICOM tags to HL7 v2 fields with conversion notes |
| Map HL7 v2 fields to FHIR R4 resources |
| Generate Mirth Connect channel configurations |
| Validate HL7 messages against the standard |
| Explain healthcare integration patterns with flow diagrams |
| Decode vendor private DICOM tags (GE, Siemens, Philips, etc.) |
| Generate realistic sample HL7 messages for testing |
PACS Connectivity Tools (Premium)
Tool | What It Does |
| Verify PACS connectivity (C-ECHO or DICOMweb ping) |
| Search for studies/series by patient, date, modality, accession |
| Retrieve detailed study/series metadata from PACS |
| C-MOVE images to a destination AE title |
| Query a study + auto-map through DICOM→HL7→FHIR with generated ORM |
Installation
Reference tools only (no PACS connectivity):
pip install dicom-hl7-mcpWith PACS connectivity (adds pynetdicom + httpx):
pip install dicom-hl7-mcp[pacs]Configuration
Basic (Reference Tools Only)
Add to your Claude Desktop config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"dicom-hl7-assistant": {
"command": "uvx",
"args": ["dicom-hl7-mcp"]
}
}
}With Premium License
{
"mcpServers": {
"dicom-hl7-assistant": {
"command": "uvx",
"args": ["dicom-hl7-mcp"],
"env": {
"DICOM_HL7_LICENSE_KEY": "your-license-key-here"
}
}
}
}With PACS Connectivity (Traditional DICOM)
Connect to a PACS using C-FIND/C-MOVE/C-ECHO:
{
"mcpServers": {
"dicom-hl7-assistant": {
"command": "uvx",
"args": ["--with", "dicom-hl7-mcp[pacs]", "dicom-hl7-mcp"],
"env": {
"DICOM_HL7_LICENSE_KEY": "your-license-key-here",
"DICOM_HL7_PACS_AE_TITLE": "YOUR_PACS",
"DICOM_HL7_PACS_HOST": "pacs.hospital.org",
"DICOM_HL7_PACS_PORT": "4242",
"DICOM_HL7_LOCAL_AE_TITLE": "CLAUDE_MCP"
}
}
}
}With PACS Connectivity (DICOMweb)
Connect to a DICOMweb-capable PACS (QIDO-RS/WADO-RS):
{
"mcpServers": {
"dicom-hl7-assistant": {
"command": "uvx",
"args": ["--with", "dicom-hl7-mcp[pacs]", "dicom-hl7-mcp"],
"env": {
"DICOM_HL7_LICENSE_KEY": "your-license-key-here",
"DICOM_HL7_DICOMWEB_URL": "https://pacs.hospital.org/dicom-web",
"DICOM_HL7_DICOMWEB_AUTH": "bearer",
"DICOM_HL7_DICOMWEB_TOKEN": "your-auth-token"
}
}
}
}Environment Variables
Variable | Required | Default | Description |
| For premium | — | Premium license key |
| No |
| Logging level |
Traditional DICOM | |||
| For DIMSE | — | Remote PACS AE title |
| For DIMSE | — | Remote PACS hostname/IP |
| For DIMSE | — | Remote PACS port |
| No |
| This server's AE title |
DICOMweb | |||
| For DICOMweb | — | DICOMweb base URL |
| No |
| Auth type: |
| For bearer | — | Bearer token |
| For basic | — | Basic auth username |
| For basic | — | Basic auth password |
Safety | |||
| No |
| Protocol: |
| No |
| Enable C-MOVE ( |
| No |
| Redact patient name/ID in output |
PHI Safety
When connected to a real PACS, query results contain Protected Health Information (PHI).
Log redaction: PHI fields are automatically stripped from all log output
Result warnings: Every PACS query result includes a PHI warning banner
Optional redaction: Set
DICOM_HL7_PHI_REDACT=trueto replace patient name/ID with[REDACTED]in tool outputNo disk caching: PACS query results are never written to disk
C-MOVE is disabled by default: Must explicitly set
DICOM_HL7_PACS_ALLOW_RETRIEVE=true
Important: Do not use PACS connectivity with cloud-hosted LLMs unless your organization's policies permit sending PHI to that LLM provider. For on-premises deployments or local LLM setups, this is not a concern.
Real-World Examples
"What is DICOM tag (0008,0050)?"
AccessionNumber — SH — RIS-generated number that identifies the order. THE key field for matching RIS orders to PACS studies.
Parse an HL7 message
"Parse this HL7 message:"
MSH|^~\&|RIS|RAD|EMR|HOSP|20240315140000||ORU^R01|MSG003|P|2.5.1 PID|1||MRN12345^^^HOSP^MR||DOE^JOHN||19650315|M OBR|1|ORD001|ACC001|CTABD^CT Abdomen^L|||20240315130000 OBX|1|FT|&GDT^Report||FINDINGS: Normal CT.||||||F
Returns each segment parsed with field names, values, table lookups, and contextual explanations.
Query PACS + Auto-Map to HL7/FHIR (Premium)
"Look up accession number ACC12345 in PACS and show me the HL7/FHIR mapping"
Returns a complete interoperability summary:
Study metadata from PACS (patient, date, modality, description)
DICOM→HL7 field mapping for every key field
HL7→FHIR R4 resource mapping
A pre-filled HL7 ORM^O01 message skeleton
Integration pattern context (IHE SWF workflow)
Map DICOM → HL7 (Premium)
"What HL7 field does DICOM Accession Number map to?"
Returns: OBR-3 / ORC-3 (Filler Order Number) with data type conversion notes (SH → EI) and mapping pitfalls.
Generate a Mirth Channel (Premium)
"Generate a Mirth channel for receiving ADT messages and writing to a FHIR server"
Returns: Complete channel config with MLLP source, FHIR HTTP destination, transformer steps, event filtering, and implementation notes.
Knowledge Base
Standards Coverage
DICOM: ~200 most common tags, SOP Classes, Transfer Syntaxes, private tag ranges for 7 vendors
HL7 v2.x: 15 segments, 20+ tables, message types (ADT, ORM, ORU, MDM, SIU, DFT, BAR), versions 2.3-2.9
FHIR R4: Mappings for Patient, Encounter, ServiceRequest, DiagnosticReport, Observation, AllergyIntolerance, Condition, RelatedPerson, Coverage
Integration Patterns: ADT Feed, Order-to-Result, Radiology Workflow (IHE SWF), Lab Interface, Report Distribution, Patient Merge, Charge Posting
Where the Knowledge Comes From
The tags, segments, and mappings are from published standards (DICOM PS3.6, HL7 v2.5.1, FHIR R4, HL7 v2-to-FHIR IG). The vendor quirks, integration tips, and "watch out for this" notes come from 16 years of building PACS/RIS/HIS interfaces in production healthcare environments.
Premium License
Free tier gives you DICOM tag lookup, HL7 parsing, and segment explanation — the tools you use every day.
Premium unlocks cross-standard mapping, Mirth generation, validation, PACS connectivity, and the deep integration knowledge that takes years to build.
Get your license: nyxtools.gumroad.com
FAQ
Do I need a license for the free tools? No. Install and use the 5 free tools immediately. No account, no sign-up.
Do I need PACS connectivity?
No. The reference and mapping tools work without any PACS connection. PACS connectivity is optional — install with pip install dicom-hl7-mcp[pacs] only if you want to query real PACS systems.
What HL7 versions are supported? v2.3 through v2.9, with focus on v2.5.1 (the most widely deployed in US healthcare).
Is this HIPAA compliant? The reference tools process standards metadata, not patient data. PACS connectivity tools access real patient data — PHI safety measures are built in (log redaction, optional output redaction, C-MOVE disabled by default), but you are responsible for ensuring use complies with your organization's policies.
What PACS systems are supported? Any PACS that supports DICOM C-FIND/C-ECHO (virtually all of them) or DICOMweb (QIDO-RS/WADO-RS). Tested with Orthanc, RamSoft, and DCM4CHEE.
Development
git clone https://github.com/NyxToolsDev/dicom-hl7-mcp-server.git
cd dicom-hl7-mcp-server
pip install -e ".[dev]"
pytestLicense
MIT License. See LICENSE.
Built by NyxTools
Available Tools
17 toolsdecode_private_tagsA
[Premium] Decode vendor-specific private DICOM tags. Returns known private tag meaning for Philips, GE, Siemens, Fuji, Agfa, Canon/Toshiba, Hologic.
Inputs: tag (required), vendor.
explain_dicom_tagA
Get a detailed explanation of a DICOM tag with context, including what it is, when it's used, common values, vendor quirks (Philips, GE, Siemens), gotchas, and related tags.
Inputs: tag (required).
explain_hl7_segmentB
Explain what an HL7 segment does and list all its fields with positions, data types, optionality, table references, and descriptions.
Inputs: segment_name (required).
explain_integration_patternA
[Premium] Explain common healthcare integration patterns including message flow diagrams, trigger events, expected segments, common pitfalls, and best practices. Patterns: 'ADT feed', 'order to result', 'radiology workflow', 'lab interface', 'report distribution', 'patient merge', 'charge posting'.
Inputs: pattern_name (required).
generate_mirth_channelA
[Premium] Generate Mirth Connect channel configuration XML. Creates a channel skeleton with source/destination connectors, transformer steps, filter logic, and implementation notes.
Inputs: source_type (required), destination_type (required), use_case (required).
generate_sample_messageA
[Premium] Generate realistic sample HL7 messages for testing. Supports ADT^A01, ADT^A04, ADT^A08, ADT^A03, ADT^A34, ADT^A40, ORM^O01, ORU^R01, MDM^T02, SIU^S12, DFT^P03.
Inputs: message_type (required), scenario.
lookup_dicom_tagA
Look up any DICOM tag by group/element number or keyword. Returns tag number, name, VR, VM, description, common values, and usage notes. Accepts formats: '0010,0010', '(0010,0010)', 'PatientName', 'patient name'.
Inputs: tag (required).
lookup_hl7_tableA
Look up HL7 table values. Returns the table name and all defined values with descriptions. Example: Table 0001 = Administrative Sex.
Inputs: table_number (required).
map_dicom_to_hl7A
[Premium] Map DICOM tags to equivalent HL7 v2 fields. Returns corresponding HL7 segment.field, mapping notes, and data type conversions.
Inputs: tag (required).
map_hl7_to_fhirA
[Premium] Map HL7 v2 segments/fields to FHIR R4 resources. Returns FHIR resource, element path, ConceptMap reference, and conversion notes.
Inputs: field_ref (required).
pacs_echoA
[Premium] Verify PACS connectivity. Sends a C-ECHO (DIMSE) or HTTP ping (DICOMweb) to confirm the PACS server is reachable and accepting connections. Returns success/failure, response time, and connection details.
Inputs: no named parameters.
pacs_get_metadataA
[Premium] Retrieve detailed metadata for a study or series from PACS. Returns DICOM header information including patient, study, series, and equipment details. Uses WADO-RS metadata (DICOMweb) or series-level C-FIND (DIMSE).
Inputs: study_instance_uid (required), series_instance_uid.
pacs_queryB
[Premium] Search PACS for studies or series. Supports filtering by patient ID, patient name, accession number, study date (YYYYMMDD or range), modality, and study description. Returns up to 50 results. Uses C-FIND (DIMSE) or QIDO-RS (DICOMweb).
Inputs: query_level, patient_id, patient_name, accession_number, +5 more.
pacs_retrieveA
[Premium] Initiate C-MOVE to send images from PACS to a destination AE title. This moves real images across the network — use with care. Only available via DIMSE protocol. Requires DICOM_HL7_PACS_ALLOW_RETRIEVE=true.
Inputs: study_instance_uid (required), destination_ae_title (required), series_instance_uid.
pacs_study_summaryA
[Premium] Query a study from PACS and show its complete interoperability mapping. Returns: (1) study metadata from PACS, (2) DICOM-to-HL7 field mapping for key fields, (3) HL7-to-FHIR resource mapping, (4) a generated HL7 ORM^O01 message skeleton pre-filled with the study's actual data. This is the bridge between 'what's in PACS' and 'how do I represent it in HL7/FHIR'. Search by Study Instance UID or accession number.
Inputs: study_instance_uid, accession_number.
parse_hl7_messageA
Parse an HL7 v2.x message into human-readable format. Returns parsed segments with field names, values, table lookups, and explanations. Supports MSH, PID, PV1, OBR, OBX, ORC, DG1, AL1, NK1, IN1, and more.
Inputs: message (required).
validate_hl7_messageA
[Premium] Validate an HL7 v2.x message against the standard. Checks required fields, data types, table values, segment structure, and cross-segment consistency.
Inputs: message (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Tools are generally well-differentated by resource and action, though 'lookup_dicom_tag' and 'explain_dicom_tag' could be confused (前者 is for dictionary lookup by number/keyword, latter for detailed educational context). Similarly, 'pacs_get_metadata' and 'pacs_study_summary' both retrieve study data but serve different use cases (raw metadata vs interoperability mapping). Overall boundaries are clear enough for correct selection.
Strong verb_noun convention throughout (e.g., decode_private_tags, explain_hl7_segment, validate_hl7_message). The PACS tools consistently use the 'pacs_' prefix, though 'pacs_study_summary' breaks the otherwise consistent pacs_verb/pacs_verb_noun pattern used by pacs_echo, pacs_query, and pacs_retrieve. Mapping tools follow consistent 'map_x_to_y' structure.
With 17 tools, the set slightly exceeds the ideal 3-15 range, but this is reasonable given the server covers three distinct healthcare standards (DICOM, HL7 v2, FHIR) plus PACS operations. Each tool addresses a specific interoperability need without redundancy; no obvious candidates for merging exist without losing clarity.
Covers the full interoperability lifecycle well: DICOM tag inspection, HL7 parsing/validation, bidirectional mapping between standards, PACS connectivity/query/retrieve, and integration pattern guidance. Minor gaps include lack of direct FHIR resource operations (only mapping to FHIR is provided) and no HL7 message transmission capabilities, though these may be outside the server's documentation-focused scope.
Maintenance
Related MCP Connectors
imonfhir.com tools: HL7 digest, Jira status, PAS validation, IG and payload compare, rule evidence.
Diagnoses, drugs & lab codes: ICD-11, LOINC, RxNorm, MeSH, ATC, CID-10. 33 tools, MIT.
Privacy-preserving synthetic health data generation. FHIR R4/R5 compliant.
Validate synthetic PAS Bundles, compare IGs and payloads, quote PAS requirements, search HL7 digest
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to query, read, download, and move medical imaging data on DICOM servers (PACS, VNA) including patient searches, study retrieval, PDF report extraction, and image transfer to AI endpoints for analysis.MIT
- FlicenseNot gradedqualityDmaintenanceExposes DICOM operations as tools for AI agents to interact with medical imaging systems and PACS. It enables searching for studies and series, querying instance metadata, and retrieving pixel data from DICOM entities.-
- AlicenseNot gradedqualityCmaintenanceEnables standardized PACS-AI integration through the Model Context Protocol, providing medical imaging workflows with DICOMweb transport, hierarchical PHI de-identification, and AI model orchestration.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables healthcare systems to parse HL7 v2 messages, convert them to FHIR R4 Bundles, validate FHIR resources, and detect/govern PHI with HIPAA, EU MDR, and GDPR compliance evidence for AI governance.MIT