dbt-mcp
dbt-mcp is a Python MCP server for Cursor with docker. A MCP (Model Context Protocol) server for interacting with dbt.
Decision snapshot
Is this a fit?
Connecting agents to external tools and data, Integrations workflows, Coding workflows, Data workflows
Cursor, Python, Docker
Check project documentation authentication
docker, Self-hosted
4 months ago · Apache-2.0 license
Requires Python. Requires Docker. Requires Apache-2.0 license.
How to use dbt-mcp
Client configuration
{
"manifest_version": "0.4",
"name": "dbt-mcp",
"display_name": "dbt MCP Server",
"version": "{dynamic-version}",
"description": "A MCP (Model Context Protocol) server for interacting with dbt.",
"long_description": "This MCP (Model Context Protocol) server provides various tools to interact with dbt. You can use this MCP server to provide AI agents with context of your project in dbt Core, dbt Fusion, and dbt Platform.",
"author": {
"name": "dbt Labs",
"url": "https://www.getdbt.com"
},
"repository": {
"type": "git",
"url": "https://github.com/dbt-labs/dbt-mcp"
},
"homepage": "https://docs.getdbt.com/docs/dbt-ai/about-mcp",
"documentation": "https://docs.getdbt.com/docs/dbt-ai/about-mcp",
"support": "https://github.com/dbt-labs/dbt-mcp/issues",
"server": {
"type": "uv",
"entry_point": "src/dbt_mcp/main.py",
"mcp_config": {
"command": "uv",
"args": [
"run",
"dbt-mcp"
],
"env": {
"DBT_HOST": "${user_config.dbt_host}"
}
}
},
"tools_generated": true,
"keywords": [
"dbt",
"data-analytics",
"data-engineering",
"llm"
],
"license": "Apache-2.0",
"privacy_policies": [
"https://www.getdbt.com/cloud/privacy-policy"
],
"compatibility": {
"platforms": [
"darwin",
"win32",
"linux"
],
"runtimes": {
"python": ">=3.12,<3.14"
}
},
"user_config": {
"dbt_host": {
"default": "cloud.getdbt.com",
"description": "Your dbt platform instance hostname (e.g., cloud.getdbt.com). You caCompatible clients
What is dbt-mcp?
dbt-mcp is a Python MCP server for Cursor with docker. A MCP (Model Context Protocol) server for interacting with dbt. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement. See how SkillIndex evaluates profiles.
Key capabilities
- Tool access support
- Shell commands support
- Document generation support
- OpenAI provider support
- Anthropic provider support
- pyproject.toml config support
- Dockerfile config support
Compatibility and setup
Install or run dbt-mcp using docker. Check dbt-labs/dbt-mcp for the latest setup command.
- Built for Python
- Built for Docker
- Install or run with docker
- Works with Cursor
- Uses SSE transport
- Database access
- Network access
MCP metadata is retained with field-level source and confidence evidence. Undetected values remain unknown.
Requirements and access
Security and permissions
Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.
When to use dbt-mcp
- Use it for connecting agents to external tools and data.
- Use it for integrations workflows.
- Use it for coding workflows.
- Use it for data workflows.
- Use it for cursor users.
Built with
Verified compatibility and discovery
Frequently asked questions
What is dbt-mcp?
dbt-mcp is a Python MCP server for Cursor with docker. A MCP (Model Context Protocol) server for interacting with dbt.
Who is dbt-mcp best for?
dbt-mcp is best for connecting agents to external tools and data, integrations workflows, coding workflows, data workflows, cursor users.
How do I install dbt-mcp?
Install or run dbt-mcp using docker. Check dbt-mcp for the latest setup command.
Is dbt-mcp actively maintained?
dbt-mcp may need a closer maintenance check before production use.
Project health auto-fetched from the source repository.
Maintain this resource?
Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.