dbt MCP Server
dbt Labs' official MCP server exposing dbt Core, Fusion and dbt Platform context to agents: SQL, Semantic Layer metrics, Discovery lineage and CLI.
Tags
Description
Tool groups include SQL (execute_sql, text_to_sql), Semantic Layer (list_metrics, query_metrics, ...), Discovery (get_lineage, get_model_health, get_node_details, ...) and dbt CLI commands. Each release also ships an experimental dbt-mcp.mcpb bundle. PyPI dbt-mcp (Python >=3.12,<3.14); latest GitHub release v2.8.0 (2026-10-13).
Related
- Model Context Protocol (MCP): Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers.
- Snowflake-managed MCP Server: Snowflake's hosted MCP server object (CREATE MCP SERVER) that exposes Cortex Agents, Cortex Analyst, Cortex Search, SQL and UDFs as governed MCP tools.
- MotherDuck / DuckDB MCP Server: MCP servers for DuckDB and MotherDuck: a managed remote server at api.motherduck.com/mcp and an open-source local server for DuckDB files, in-memory DBs and S3.
Sources
- https://github.com/dbt-labs/dbt-mcp
- https://github.com/dbt-labs/dbt-mcp/releases
- https://pypi.org/project/dbt-mcp/
- https://docs.getdbt.com/docs/dbt-ai/about-mcp
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)