Provides tools for validating, explaining, and remediating clinical supply data quality across Bronze, Silver, and Gold layers using Unity Catalog and Delta tables on Azure Databricks.
Integrates with Azure OpenAI to power agent-based data quality analysis, root cause analysis, and natural language queries about clinical supply data.
Supports validation and ingestion of SAP batch raw data as part of clinical supply chain data processing pipelines.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Clinical MCP Server validate the sap_batch_raw table"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI-powered platform that validates, explains, and remediates clinical supply data quality across Bronze → Silver → Gold on Azure Databricks, with governed MCP tools, data contracts, and an evaluation harness mapped to G7 Engineer II criteria T1 / T2 / T3.
Storage: Databricks only — Unity Catalog Volumes for landing files and managed Delta tables for Bronze/Silver/Gold. No separate Azure Data Lake / ADLS account in this design.
python -m venv .venv
# Windows
.venv\Scripts\activate
pip install -r requirements.txt
# List contracts
python -m clinical_platform.cli list-contracts
# Happy-path validation
python -m clinical_platform.cli validate sap_batch_raw
# Portfolio demo — schema drift
python -m clinical_platform.cli demo-drift
# Agents
python -m agents.cli dq --drift
python -m agents.cli rca
python -m agents.cli ask "Why did Gold trial inventory fail today?"
# T3 evaluation
python -m eval.harnessCopy .env.example → .env when you wire Azure OpenAI (offline fallback works without it).
Related MCP server: mcp-databricks
contracts/ # Unity Catalog contracts (catalog.schema.table)
hive_metastore/ # Hive metastore track (database.table) — use if no UC create permission
clinical_platform/ # validate_table, expectations, local engine
mcp_server/ # Governed tools for agents
agents/ # DQ, RCA, Q&A
...
metadata/ddl.sql # Unity Catalog DDL
hive_metastore/ddl.sql # Hive metastore DDLNo Unity Catalog create rights? Use hive_metastore/README.md.
Criterion | What this repo proves |
T1 | MCP tool server, reusable agent skills, prompt-backed RCA/Q&A, knowledge via contracts/lineage |
T2 | Contract-driven validation, quality reports, lineage stubs, GxP-gated remediation proposals |
T3 | Golden eval set, keyword/tool groundedness scores, versioned prompts, nightly job stub |
Run metadata/ddl.sql in your workspace (creates catalogs, schemas, Volumes, metadata tables).
Sync contracts into clinical_supply.metadata.table_contracts.
Land source files in /Volumes/clinical_supply/bronze/landing/ (not ADLS).
Point notebooks at cluster libraries (pip install -e .).
Deploy workflows/databricks.yml with Databricks Asset Bundles.
Replace local engine with Spark/Great Expectations runner when ready.
This server cannot be deployed
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Auto-discover validation rules from data — scan, profile, health-score. No rules to write.
Knowledge coverage map and health score. Ingest docs into a governed knowledge graph via MCP.
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
