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.
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
Maintainer
Works with
Installation
Manual Installation
npx dbt-doctorConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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
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-doctorCompile 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 compileAdd 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"
}
}
}
}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.
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.
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.
Dbt Doctor Alternatives — Similar Analytics Servers
Looking for alternatives to Dbt Doctor? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
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.
Set Up Dbt Doctor in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.