dbt
MCP server by dbt Labs
Give assistants dbt project context: models, lineage, Semantic Layer metrics, Discovery API data and dbt CLI commands.
Install dbt
Runs on your machine. Your client starts it with this command:
Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.
DBT_PROJECT_DIRPath to your dbt project.DBT_PATHPath to the dbt executable.
Share this server
Opens this page, with the install command and setup steps.
mcp.tc/i/dbtAbout
Connects an AI assistant to dbt Core, dbt Fusion and the dbt platform. It can list models, sources and exposures, trace lineage, query Semantic Layer metrics, run dbt CLI commands, generate YAML and staging models, manage platform jobs and runs, and fetch pages from the dbt docs.
It runs locally over stdio with uvx dbt-mcp. The CLI tools need DBT_PROJECT_DIR and DBT_PATH. Semantic Layer, Discovery, Admin API and SQL tools need a dbt platform host (DBT_HOST) and a token (DBT_TOKEN). CLI commands such as run and build can modify warehouse objects, so use them only with a client you trust.
What you can do
- Query Semantic Layer metrics, dimensions and entities
- Browse models, sources, macros and exposures via the Discovery API
- Trace model and column-level lineage
- Run dbt build, run, test, compile and show from the CLI
- Generate source YAML, model YAML and staging models
- List, trigger, retry and cancel dbt platform jobs and runs
- Search and fetch official dbt documentation pages
Tools
Local servers list their tools once they’re running, so we can’t show them here. Look for the list in its documentation; your client shows them after you add it.
Example prompts
List all metrics defined in our dbt Semantic Layer
Show the upstream and downstream lineage of the orders model
Run dbt test for the staging models and summarize failures
Generate staging model SQL for the raw customers source table
Set up
Every client starts dbt on your machine with the same command. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport stdio dbt --env "DBT_PROJECT_DIR=<YOUR_DBT_PROJECT_DIR>" --env "DBT_PATH=<YOUR_DBT_PATH>" -- uvx dbt-mcp- Start Claude Code and type
/mcp. dbt should show as connected.
Add --scope user to make it available in every project. Replace the placeholders with your own values.
Claude Desktop
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<YOUR_DBT_PROJECT_DIR>",
"DBT_PATH": "<YOUR_DBT_PATH>"
}
}
}
}- Save the file and restart Claude Desktop. Replace the placeholders with your own values.
Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<YOUR_DBT_PROJECT_DIR>",
"DBT_PATH": "<YOUR_DBT_PATH>"
}
}
}
}Needs uv (Python) on your computer. Replace the placeholders with your own values.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"dbt","type":"stdio","command":"uvx","args":["dbt-mcp"],"env":{"DBT_PROJECT_DIR":"<YOUR_DBT_PROJECT_DIR>","DBT_PATH":"<YOUR_DBT_PATH>"}}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"dbt": {
"type": "stdio",
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<YOUR_DBT_PROJECT_DIR>",
"DBT_PATH": "<YOUR_DBT_PATH>"
}
}
}
}Needs uv (Python) on your computer.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<YOUR_DBT_PROJECT_DIR>",
"DBT_PATH": "<YOUR_DBT_PATH>"
}
}
}
}- Refresh the MCP server list in Cascade. Replace the placeholders with your own values.
Devin Desktop is the new name for Windsurf.
Codex
codex mcp add dbt --env "DBT_PROJECT_DIR=<YOUR_DBT_PROJECT_DIR>" --env "DBT_PATH=<YOUR_DBT_PATH>" -- uvx dbt-mcpOr edit ~/.codex/config.toml directly:
[mcp_servers.dbt]
command = "uvx"
args = ["dbt-mcp"]
env = { DBT_PROJECT_DIR = "<YOUR_DBT_PROJECT_DIR>", DBT_PATH = "<YOUR_DBT_PATH>" }Needs uv (Python) on your computer. Replace the placeholders with your own values.
Gemini CLI
gemini mcp add -e "DBT_PROJECT_DIR=<YOUR_DBT_PROJECT_DIR>" -e "DBT_PATH=<YOUR_DBT_PATH>" dbt uvx dbt-mcpThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients that start local servers accept this shape:
{
"mcpServers": {
"dbt": {
"command": "uvx",
"args": [
"dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<YOUR_DBT_PROJECT_DIR>",
"DBT_PATH": "<YOUR_DBT_PATH>"
}
}
}
}Zed puts servers under context_servers in its settings, with the same command, args and env fields.
Needs uv (Python) on your computer. Replace the placeholders with your own values.
Embed
Show dbt in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/dbt)<a href="https://mcp.tc/i/dbt"><img src="https://mcp.tc/i/dbt/badge.svg" alt="dbt on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/dbt.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/dbt" title="dbt on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/dbt.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the dbt card to your site.
Add the mcp.tc card for dbt, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/dbt.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="dbt"><a href="https://mcp.tc/i/dbt">dbt on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/dbt)
```
Reference: https://mcp.tc/embedChange history
This server runs on your computer, so we follow its PyPI package: each new version shows up here, with edits by its owner.
-
New version 2.10.2 (was 2.10.1). Read from PyPI.
-
New version 2.10.1 (was 2.10.0). Read from PyPI.
-
New version 2.10.0 (was 2.9.0). Read from PyPI.
-
New version 2.9.0 (was 2.8.0). Read from PyPI.
-
New version 2.8.0 (was 2.7.0). Read from PyPI.
-
New version 2.7.0 (was 2.6.0). Read from PyPI.
-
Tracking started: version 2.6.0.
FAQ
Can I paste mcp.tc/i/dbt into my MCP client?
No. dbt runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx dbt-mcp.
Does dbt need an API key?
No. It reads DBT_PROJECT_DIR and DBT_PATH from its environment; the setup steps show where to set them.
Is dbt a remote or a local server?
Local. Your client starts it as a process on your computer with uvx dbt-mcp, which needs uv (Python).
What can dbt do?
You can query Semantic Layer metrics, dimensions and entities, browse models, sources, macros and exposures via the Discovery API and trace model and column-level lineage.
Which clients can use it?
Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.
Does mcp.tc track changes to dbt?
Partly. It runs on your computer, so we follow its PyPI package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read dbt’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with dbt Labs. This page was built from dbt’s public metadata, last checked on 3 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.