Configuring Dbt Mcp Server

This walks you through the entire dbt MCP server setup process, from deciding between local (uvx) versus remote (HTTP) deployment to generating the actual JSON config for your client. It asks the right questions upfront (which client, what use case, which tools to enable) and gives you templated configs for Claude Desktop, Claude Code, Cursor, and VS Code. The decision flow is sensible: local if you need CLI access for development work, remote if you're just querying metrics and metadata. Particularly good on credential security, explicitly telling you to use environment variable references instead of hardcoded tokens. The only gap is it cuts off mid-sentence in the Claude Code section, but everything before that is solid reference material for first-time setup or troubleshooting connection issues.

skills.sh installs: 1.1K
GitHub stars: 759
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add dbt-labs/dbt-agent-skills --skill configuring-dbt-mcp-server --agent claude-code

Installs into .claude/skills of the current project.

Files

Configure dbt MCP Server

Overview

The dbt MCP server connects AI tools to dbt's CLI, Semantic Layer, Discovery API, and Admin API. This skill guides users through setup with the correct configuration for their use case.

Decision Flow

flowchart TB
    start([User wants dbt MCP]) --> q1{Local or Remote?}
    q1 -->|dev workflows,<br>CLI access needed| local[Local Server<br>uvx dbt-mcp]
    q1 -->|consumption only,<br>no local install| remote[Remote Server<br>HTTP endpoint]
    local --> q2{Which client?}
    remote --> q2
    q2 --> claude_desktop[Claude Desktop]
    q2 --> claude_code[Claude Code]
    q2 --> cursor[Cursor]
    q2 --> vscode[VS Code]
    claude_desktop --> config[Generate config<br>+ test setup]
    claude_code --> config
    cursor --> config
    vscode --> config