dbt-mcp
Verified Safeby dbt-labs
Overview
Provides AI agents with tools to interact with dbt Core, dbt Fusion, and dbt Platform, enabling advanced data analytics and project management capabilities within a model context protocol (MCP) server.
Installation
uv run dbt-mcpEnvironment Variables
- OPENAI_API_KEY
- DBT_TOKEN
- DBT_HOST
- DBT_PROD_ENV_ID
- DBT_DEV_ENV_ID
- DBT_USER_ID
- DBT_PROJECT_DIR
- DBT_PATH
- MCP_TRANSPORT
Security Notes
The server processes tool arguments from LLM responses using `json.loads`. While `pydantic` validation follows this, parsing potentially untrusted JSON prior to validation could pose a risk (e.g., resource exhaustion). The local OAuth server's `/shutdown` endpoint, intended for graceful self-termination, could be a minor concern if exposed outside a local-only context without authentication. The `OAUTH_CLIENT_ID` is hardcoded but is a public client identifier.
Similar Servers
mcp-server
Provides a Model Context Protocol (MCP) server for AI agents to search and retrieve curated documentation for the Strands Agents framework, facilitating AI coding assistance.
mcp-servers
Provides a curated collection of Model Context Protocol (MCP) server configurations to enable AI agents to interact with various developer tools and services.
zeromcp
A minimal, pure Python Model Context Protocol (MCP) server for exposing tools, resources, and prompts via HTTP/SSE and Stdio transports.
1xn-vmcp
An open-source platform for composing, customizing, and extending multiple Model Context Protocol (MCP) servers into a single logical, virtual MCP server, enabling fine-grained context engineering for AI workflows and agents.