{
  "markdown": "# K01 MCP Server\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![MCP](https://img.shields.io/badge/MCP-compatible-green.svg)](https://modelcontextprotocol.io)\n\nGenerate and query clinically realistic synthetic health data directly from your AI workflow.\n\n---\n\nK01'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.\n\n> This repository contains documentation and configuration for the K01 MCP server. The server implementation is proprietary and runs on K01 infrastructure.\n\n## Available Tools\n\n| Tool | Description | Key Parameters |\n|------|-------------|----------------|\n| `generate_synthetic_cohort` | Generate synthetic patient cohorts with demographic and clinical constraints | `count`, `age_min`/`age_max`, `gender`, `condition` (ICD-10), `seed`, `locale` |\n| `search_patients` | Search a virtual patient database with advanced healthcare filters | `gender`, `birthdate`, `numberOfMedicinesFrom`/`To`, `conditionTypes`, `locale` |\n| `get_patient_record` | Retrieve a complete patient record with medication and condition summaries | `patient_id`, `fhir_version` |\n| `get_patient_medications` | Get detailed medication records with ATC codes and therapeutic indications | `patient_id`, `seed`, `fhir_version` |\n| `get_patient_conditions` | Retrieve patient conditions with ICD-10 codes and localized names | `patient_id`, `seed`, `fhir_version` |\n| `compare_fhir_versions` | Compare the same patient data across FHIR R4 and R5 | `patient_id`, `resource_type` |\n\nAll tools support both FHIR R4 and R5. See [docs/tools.md](docs/tools.md) for full parameter documentation.\n\n## Quick Start\n\n### Claude Desktop\n\nAdd to your Claude Desktop configuration (`Settings > MCP Servers`):\n\n```json\n{\n  \"mcpServers\": {\n    \"k01\": {\n      \"url\": \"https://mcp.k01.is/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to your Cursor MCP configuration (`.cursor/mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"k01\": {\n      \"url\": \"https://mcp.k01.is/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\nRestart the application after adding the configuration. The K01 tools will appear in the tool list.\n\n## Authentication\n\nThe K01 MCP server uses Bearer token authentication. Include your API key in the `Authorization` header.\n\nTo get an API key, contact K01 at [k01.is](https://k01.is). Self-service key provisioning is coming soon.\n\nSee [docs/authentication.md](docs/authentication.md) for details.\n\n## Examples\n\n### Generate a diabetic cohort\n\n> \"Generate 100 patients aged 40-65 with Type 2 diabetes\"\n\nThe `generate_synthetic_cohort` tool creates a FHIR Bundle with Patient, Condition, MedicationStatement, Procedure, and Observation resources:\n\n```\ngenerate_synthetic_cohort(count=100, age_min=40, age_max=65, condition=\"E11.9\", seed=42)\n```\n\n### Search for complex patients\n\n> \"Find patients with 3+ medications and chronic conditions\"\n\n```\nsearch_patients(numberOfMedicinesFrom=3, conditionTypes=\"chronic\", _count=20)\n```\n\n### Compare FHIR versions\n\n> \"How do this patient's medications look in R4 vs R5?\"\n\n```\ncompare_fhir_versions(patient_id=\"0101302989\", resource_type=\"Medication\")\n```\n\nSee [docs/examples.md](docs/examples.md) for more workflows.\n\n## Privacy and Security\n\nAll data generated by K01 is fully synthetic. No real patient data is used, stored, or referenced at any point in the pipeline.\n\n- **Differential privacy** — noise injection with configurable epsilon values ensures generated distributions cannot be reverse-engineered to identify real individuals\n- **No training on real data** — the generation models are built from published clinical statistics and pharmacological references, not patient records\n- **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\n- **Deterministic seeding** — use seeds for reproducible results without persisting any patient data server-side\n\n## Links\n\n- [K01 Website](https://k01.is)\n- [API Documentation](https://k01.is/docs)\n- [Tool Reference](docs/tools.md)\n- [Authentication Guide](docs/authentication.md)\n- [Usage Examples](docs/examples.md)\n- [FAQ](docs/faq.md)\n- [MCP Protocol](https://modelcontextprotocol.io)\n\n## License\n\nThis repository (documentation, configuration, and examples) is licensed under [MIT](LICENSE). The K01 server implementation is proprietary.\n",
  "bytes": 4725,
  "sha": "cf94821311badf7d2f100926335b9cc171a092e247c8e7518fe208912b877847",
  "repo_slug": "k01labs/k01-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_is_k01_synthetic_health_data_59733f13/readme"
}