Collaboration, Harmonization

This article describes what you can do in the Collaboration and Harmonization capability areas, with example prompts for each action.

Note: The underlying tool names and implementation details in this section are subject to change as the MCP server evolves. You do not need to know the tool names to use the MCP server — simply describe what you want to do in natural language and your AI assistant will handle the rest.

Collaboration

Collaboration tools let you manage who has access to a project and check the health of your federated network before running jobs.

Viewing and managing collaborators

List all collaborators on a project, invite new users or sites, or remove access for someone who should no longer be on the project.

• "Who has access to the oncology project?"
• "List all collaborators and their roles in the trial project."
• "Invite jane@hospital.org to the oncology project as an analyst."
• "Add site-b@partner.org to the trial project."
• "Remove john@hospital.org from the oncology project."

Checking workgroup and site connectivity

Before submitting a long-running federated job, check that all required sites are online and reachable.

• "Are all sites in my workgroup online?"
• "Check the connectivity status of the sites in the oncology project before I run the analysis."
• "When was Site B last seen?"

Harmonization

Harmonization tools allow you to map source datasets from participating sites to a common schema or standard medical vocabulary, then run the transformation federatedly. Transformed data stays at each site — no raw data is centralised at any point.

Managing harmonization schemas

Schemas define the target structure that source datasets are mapped to. You can list, inspect, create, and delete schemas through conversation.

• "What harmonization schemas are available in my workgroup?"
• "Show me the columns defined in the OMOP patient schema."
• "Create a new harmonization schema called 'Standard Admissions' with columns for patient_id, admission_date, diagnosis_code, and los_days."
• "Delete the 'Draft Schema v1' schema."

Browsing medical vocabularies

Look up standard medical vocabulary concepts before constructing mappings. Supported vocabularies include OMOP CDM, SNOMED CT, ICD-10, LOINC, and RxNorm.

• "Find the SNOMED concept ID for 'type 2 diabetes mellitus'."
• "Look up ICD-10 codes related to heart failure."
• "What is the LOINC code for serum creatinine?"
• "Search the RxNorm vocabulary for metformin."

Creating semantic mappings

Use AI-assisted semantic mapping to generate suggested mappings from your source dataset's columns and values to standard vocabulary concepts. Suggestions come with confidence scores for you to review before applying.

• "Generate an OMOP semantic mapping for the admissions dataset."
• "Suggest SNOMED mappings for the diagnosis codes in the trial dataset."
• "What standard concepts do the values in the 'procedure_type' column map to?"

Creating syntactic mappings

Syntactic mapping defines the structural field-level mapping between your source dataset's column names and the target schema's column names, independent of medical concept meaning.

• "Map the 'pt_id' column in my dataset to 'patient_id' in the standard admissions schema."
• "Create a field mapping from the trial dataset to the Standard Admissions schema."

Running the harmonization pipeline

Once your semantic and syntactic mappings are in place, run the full harmonization pipeline to transform the source dataset to the target schema across all sites.

• "Run the harmonization pipeline on the admissions dataset using the Standard Admissions schema."
• "Harmonize the trial data to OMOP CDM format and save the result as 'OMOP Trial Cohort'."
• "Transform the patient dataset to the standard schema across all three sites."