Mcp Databricks — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Databricks (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
mcp-databricks/
├── .env # Environment variables (DATABRICKS_HOST, TOKEN, etc.)
├── Dockerfile # Containerization for deployment
├── README.md
├── pyproject.toml # or requirement.txt
└── src/
├── __init__.py
├── server.py # Server entrypoint, initializes MCP server and registers tools
├── config.py # Configuration management using Pydantic Settings
├── db/
│ ├── __init__.py
│ ├── client.py # Databricks SQL connection pool / Databricks SDK client
│ └── operations.py # Low-level SQL execution & metadata query logic
├── models/
│ ├── __init__.py
│ ├── metadata.py # Pydantic models for Table/Column schemas and discovery
│ └── operations.py # Pydantic models for Alter/Write request payloads
└── tools/
├── __init__.py
├── metadata.py # MCP tools for reading tables and discovery
└── warehouse.py # MCP tools for altering columns and DDL operations
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.