dbt-core-mcp and dbt-doctor
The two tools are complementary, as "dbt-core-mcp" provides the foundational Model Context Protocol server for interacting with dbt projects, while "dbt-doctor" leverages that protocol to offer advanced AI-driven quality, governance, and documentation features.
About dbt-core-mcp
NiclasOlofsson/dbt-core-mcp
dbt Core MCP Server: Interact with dbt projects via Model Context Protocol
Executes dbt commands (runs, tests, builds) within the user's actual environment without requiring dbt-core or adapters to be installed server-side, automatically detecting and respecting the Python environment (uv, poetry, venv, conda) and dbt version in use. Integrates with Claude and other MCP-compatible AI assistants via VS Code, providing full project awareness including lineage analysis, compiled SQL inspection, and CTE debugging to enable true pair-programming workflows without context switching.
About dbt-doctor
Astoriel/dbt-doctor
AI-driven quality & governance MCP Server for dbt projects. Audit coverage, profile data, detect schema drift, and auto-generate documentation — all through natural language with your AI assistant.
Implements the Model Context Protocol (MCP) to expose 12+ tools covering project auditing, data profiling via single-pass SQL queries, schema drift detection, and intelligent test suggestions based on column statistics. Operates as a read-only analysis layer with safe YAML writes using `ruamel.yaml` to preserve existing formatting and comments, integrating directly with Claude Desktop and Cursor via stdio transport and requiring only a compiled dbt manifest to function.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work