K01 Synthetic Health Data

Install

Config snippet generator goes here (5 client tabs)

README

# K01 MCP Server

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
[![MCP](https://img.shields.io/badge/MCP-compatible-green.svg)](https://modelcontextprotocol.io)

Generate and query clinically realistic synthetic health data directly from your AI workflow.

---

K01's MCP server gives AI agents and LLM-powered tools access to privacy-preserving synthetic health data generation. Generate FHIR-compliant patient cohorts, query structured EHR data, and compare across FHIR versions — all with built-in differential privacy. No real patient data is involved at any point.

> This repository contains documentation and configuration for the K01 MCP server. The server implementation is proprietary and runs on K01 infrastructure.

## Available Tools

| Tool | Description | Key Parameters |
|------|-------------|----------------|
| `generate_synthetic_cohort` | Generate synthetic patient cohorts with demographic and clinical constraints | `count`, `age_min`/`age_max`, `gender`, `condition` (ICD-10), `seed`, `locale` |
| `search_patients` | Search a virtual patient database with advanced healthcare filters | `gender`, `birthdate`, `numberOfMedicinesFrom`/`To`, `conditionTypes`, `locale` |
| `get_patient_record` | Retrieve a complete patient record with medication and condition summaries | `patient_id`, `fhir_version` |
| `get_patient_medications` | Get detailed medication records with ATC codes and therapeutic indications | `patient_id`, `seed`, `fhir_version` |
| `get_patient_conditions` | Retrieve patient conditions with ICD-10 codes and localized names | `patient_id`, `seed`, `fhir_version` |
| `compare_fhir_versions` | Compare the same patient data across FHIR R4 and R5 | `patient_id`, `resource_type` |

All tools support both FHIR R4 and R5. See [docs/tools.md](docs/tools.md) for full parameter documentation.

## Quick Start

### Claude Desktop

Add to your Claude Desktop configuration (`Settings > MCP Servers`):

```json
{
  "mcpServers": {
    "k01": {
      "url": "https://mcp.k01.is/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

### Cursor

Add to your Cursor MCP configuration (`.cursor/mcp.json`):

```json
{
  "mcpServers": {
    "k01": {
      "url": "https://mcp.k01.is/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

Restart the application after adding the configuration. The K01 tools will appear in the tool list.

## Authentication

The K01 MCP server uses Bearer token authentication. Include your API key in the `Authorization` header.

To get an API key, contact K01 at [k01.is](https://k01.is). Self-service key provisioning is coming soon.

See [docs/authentication.md](docs/authentication.md) for details.

## Examples

### Generate a diabetic cohort

> "Generate 100 patients aged 40-65 with Type 2 diabetes"

The `generate_synthetic_cohort` tool creates a FHIR Bundle with Patient, Condition, MedicationStatement, Procedure, and Observation resources:

```
generate_synthetic_cohort(count=100, age_min=40, age_max=65, condition="E11.9", seed=42)
```

### Search for complex patients

> "Find patients with 3+ medications and chronic conditions"

```
search_patients(numberOfMedicinesFrom=3, conditionTypes="chronic", _count=20)
```

### Compare FHIR versions

> "How do this patient's medications look in R4 vs R5?"

```
compare_fhir_versions(patient_id="0101302989", resource_type="Medication")
```

See [docs/examples.md](docs/examples.md) for more workflows.

## Privacy and Security

All data generated by K01 is fully synthetic. No real patient data is used, stored, or referenced at any point in the pipeline.

- **Differential privacy** — noise injection with configurable epsilon values ensures generated distributions cannot be reverse-engineered to identify real individuals
- **No training on real data** — the generation models are built from published clinical statistics and pharmacological references, not patient records
- **FHIR-compliant output** — all resources conform to HL7 FHIR R4/R5 specifications, making them safe drop-in replacements for real data in development and testing
- **Deterministic seeding** — use seeds for reproducible results without persisting any patient data server-side

## Links

- [K01 Website](https://k01.is)
- [API Documentation](https://k01.is/docs)
- [Tool Reference](docs/tools.md)
- [Authentication Guide](docs/authentication.md)
- [Usage Examples](docs/examples.md)
- [FAQ](docs/faq.md)
- [MCP Protocol](https://modelcontextprotocol.io)

## License

This repository (documentation, configuration, and examples) is licensed under [MIT](LICENSE). The K01 server implementation is proprietary.