Dbt Doctor

v1.0.0Analyticsstable

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.

auditdbt-packagesmcp-server
Share:
140
Stars
0
Downloads
0
Weekly
0/5

What is Dbt Doctor?

Dbt Doctor is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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.

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.

This server falls under the Analytics and Data Science & ML categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • AI-driven quality & governance MCP Server for dbt projects.

Use Cases

Audit dbt project quality and detect schema drift automatically.
Generate comprehensive documentation and detect coverage gaps through natural language.
Astoriel

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx dbt-doctor

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Dbt Doctor

dbt-doctor is an AI-driven quality and governance MCP server for dbt projects that lets you audit, profile, and document your data models through natural language. It exposes 12 tools covering project health scoring, test coverage analysis, DAG inspection, column-level profiling with NULL rates and cardinality, schema drift detection, test suggestion, and automated YAML documentation updates. Instead of running CLI commands and manually reading manifests, you can ask your AI assistant to diagnose your dbt project in real time and generate or update schema.yml files directly.

Prerequisites

  • Python 3.9+ with pip installed
  • An existing dbt project with a compiled manifest.json (run `dbt compile` or `dbt run` first)
  • Database credentials configured in your dbt profiles.yml so dbt-doctor can execute profiling queries
  • An MCP-compatible client such as Claude Desktop or Cursor
1

Install dbt-doctor from PyPI

Install the package globally or inside a virtual environment. It bundles its own MCP server entry point.

pip install dbt-doctor
2

Compile your dbt project

dbt-doctor reads the compiled manifest to understand your project structure. Run dbt compile in your project directory to produce an up-to-date manifest.json.

cd /path/to/your/dbt/project
dbt compile
3

Add dbt-doctor to your MCP client configuration

Register the server in your claude_desktop_config.json. Point DBT_PROJECT_DIR to your dbt project root so the server can locate profiles.yml and manifest.json.

{
  "mcpServers": {
    "dbt-doctor": {
      "command": "python",
      "args": ["-m", "dbt_doctor.mcp_server"],
      "env": {
        "DBT_PROJECT_DIR": "/path/to/your/dbt/project"
      }
    }
  }
}
4

Restart your MCP client

Quit and reopen Claude Desktop (or reload your MCP server list). The 12 dbt-doctor tools — including audit_project, profile_model, and detect_schema_drift — should now appear.

5

Run a project health check

Start with a broad health audit to see overall scores and identify which models have the lowest test coverage or the most issues.

6

Profile a model and generate tests

Use the AI assistant to profile a specific model, then request auto-generated test suggestions based on the column statistics returned.

Dbt Doctor Examples

Client configuration

Example claude_desktop_config.json for running the dbt-doctor MCP server against a local dbt project.

{
  "mcpServers": {
    "dbt-doctor": {
      "command": "python",
      "args": ["-m", "dbt_doctor.mcp_server"],
      "env": {
        "DBT_PROJECT_DIR": "/Users/yourname/projects/my_dbt_project"
      }
    }
  }
}

Prompts to try

Natural-language prompts that exercise dbt-doctor's 12 audit and documentation tools.

- "What is the overall health of my dbt project? Show me models with missing tests."
- "Profile the fct_orders model and tell me about NULL rates and cardinality for each column"
- "Detect any schema drift between my database and the current dbt manifest"
- "Suggest tests for the dim_customers model based on its column statistics"
- "Generate documentation for the stg_payments model and update its schema.yml"

Troubleshooting Dbt Doctor

Server fails to start with 'manifest.json not found'

Run `dbt compile` or `dbt run` in your dbt project directory first to generate the manifest. Confirm that DBT_PROJECT_DIR in the MCP config points to the directory containing dbt_project.yml.

Profile queries fail with database connection errors

Verify your dbt profiles.yml is correctly configured and that `dbt debug` succeeds from the project directory. dbt-doctor uses the same profile connection, so any credentials issue will surface as profiling failures.

update_model_yaml overwrites custom comments in schema.yml

dbt-doctor uses a YAML-safe writer that preserves existing comments, but always commit or back up your schema.yml before running generation tools in case of unexpected overwrites on complex anchor/alias constructs.

Frequently Asked Questions about Dbt Doctor

What is Dbt Doctor?

Dbt Doctor is a Model Context Protocol (MCP) server that 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. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Dbt Doctor?

Follow the installation instructions on the Dbt Doctor GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Dbt Doctor?

Dbt Doctor works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Dbt Doctor free to use?

Yes, Dbt Doctor is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Analytics MCP Servers

Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "dbt-doctor": { "command": "npx", "args": ["-y", "dbt-doctor"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Dbt Doctor?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides