databricks-mcp
Read-only Databricks SQL analytics MCP for safe agent exploration, profiling and querying without mutation risk.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for databricks-mcp, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
databricks-mcp gives AI agents safe, read-only SQL analytics over Databricks, supporting exploration, profiling and querying without mutation risk. Security surface: it holds a DATABRICKS_TOKEN and HTTP path to a warehouse; the read-only design plus a MAX_ROWS cap are the guardrails against data exfiltration through injected queries.
Key features
- Read-only Databricks SQL access
- Data profiling and exploration
- Configurable MAX_ROWS cap
- Token-based warehouse auth
Use cases
- Explore a Databricks lakehouse from an agent
- Profile tables without write risk