configuring-dbt-mcp-server

Name: configuring-dbt-mcp-server
Author: dbt-labs

637stars55forks

How to install configuring-dbt-mcp-server?

dbt-labs/dbt-agent-skills/configuring-dbt-mcp-server

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

Installs into the current project.

Summary

Generates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt. Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.

Files · 1

View on GitHub

SKILL.md

1	# Configure dbt MCP Server
2
3	## Overview
4
5	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.
6
7	## Decision Flow
8
9	```mermaid
10	flowchart TB
11	start([User wants dbt MCP]) --> q1{Local or Remote?}
12	q1 -->\|dev workflows,<br>CLI access needed\| local[Local Server<br>uvx dbt-mcp]
13	q1 -->\|consumption only,<br>no local install\| remote[Remote Server<br>HTTP endpoint]
14	local --> q2{Which client?}
15	remote --> q2
16	q2 --> claude_desktop[Claude Desktop]
17	q2 --> claude_code[Claude Code]
18	q2 --> cursor[Cursor]
19	q2 --> vscode[VS Code]
20	claude_desktop --> config[Generate config<br>+ test setup]
21	claude_code --> config
22	cursor --> config
23	vscode --> config
24	```
25
26	## Questions to Ask
27
28	### 1. Server Type
29	Ask: "Do you want to use the local or remote dbt MCP server?"
30
31	\| Local Server \| Remote Server \|
32	\| -------------------------------------------------------------------------------------------------------------------------------------------------------- \| ----------------------------------------------------------- \|
33	\| Runs on your machine via `uvx` \| Connects via HTTP to dbt platform \|
34	\| Required for development (authoring models, tests, docs) but can also connect to the dbt platform for consumption (querying metrics, exploring metadata) \| Best for consumption (querying metrics, exploring metadata) \|
35	\| Supports dbt CLI commands (run, build, test, show) \| No CLI commands (run, build, test) \|
36	\| Works without a dbt platform account but can also connect to the dbt platform for development (authoring models, tests, docs) \| Requires dbt platform account \|
37	\| No credit consumption \| Consumes dbt Copilot credits \|
38
39	### 2. MCP Client
40	Ask: "Which MCP client are you using?"
41	- Claude Desktop
42	- Claude Code (CLI)
43	- Cursor
44	- VS Code
45
46	### 3. Use Case (Local Server Only)
47	Ask: "What's your use case?"
48
49	\| CLI Only \| Platform Only \| Platform + CLI \|
50	\|----------\|---------------\|----------------\|
51	\| dbt Core/Fusion users \| dbt Cloud without local project \| Full access to both \|
52	\| No platform account needed \| OAuth or token auth \| Requires paths + credentials \|
53
54	### 4. Tools to Enable
55	Ask: "Which tools do you want enabled?" (show defaults)
56
57	\| Tool Category \| Default \| Environment Variable \|
58	\|---------------\|---------\|---------------------\|
59	\| dbt CLI (run, build, test, compile) \| Enabled \| `DISABLE_DBT_CLI=true` to disable \|
60	\| Semantic Layer (metrics, dimensions) \| Enabled \| `DISABLE_SEMANTIC_LAYER=true` to disable \|
61	\| Discovery API (models, lineage) \| Enabled \| `DISABLE_DISCOVERY=true` to disable \|
62	\| Admin API (jobs, runs) \| Enabled \| `DISABLE_ADMIN_API=true` to disable \|
63	\| SQL (text_to_sql, execute_sql) \| Disabled \| `DISABLE_SQL=false` to enable \|
64	\| Codegen (generate models/sources) \| Disabled \| `DISABLE_DBT_CODEGEN=false` to enable \|
65
66	## Prerequisites
67
68	### Local Server
69	1. Install `uv`: https://docs.astral.sh/uv/getting-started/installation/
70	2. Have a dbt project (for CLI commands)
71	3. Find paths:
72	- `DBT_PROJECT_DIR`: Folder containing `dbt_project.yml`
73	- macOS/Linux: `pwd` from project folder
74	- Windows: Full path with forward slashes (e.g., `C:/Users/name/project`)
75	- `DBT_PATH`: Path to dbt executable
76	- macOS/Linux: `which dbt`
77	- Windows: `where dbt`
78
79	### Remote Server
80	1. dbt Cloud account with AI features enabled
81	2. Production environment ID (from Orchestration page)
82	3. Personal access token or service token
83
84	See [How to Find Your Credentials](references/finding-credentials.md) for detailed guidance on obtaining tokens and IDs.
85
86	## Credential Security
87
88	- Always use environment variable references (e.g., `${DBT_TOKEN}`) instead of literal token values in configuration files that may be committed to version control
89	- Never log, display, or echo token values in terminal output
90	- When using `.en

People who liked this also viewed

6 picks

Type

configuring-dbt-mcp-server

637stars55forks

View on GitHub

How to install configuring-dbt-mcp-server?

dbt-labs/dbt-agent-skills/configuring-dbt-mcp-server

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Configure dbt MCP Server
2
3	## Overview
4
5	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.
6
7	## Decision Flow
8
9	```mermaid
10	flowchart TB
11	start([User wants dbt MCP]) --> q1{Local or Remote?}
12	q1 -->\|dev workflows,<br>CLI access needed\| local[Local Server<br>uvx dbt-mcp]
13	q1 -->\|consumption only,<br>no local install\| remote[Remote Server<br>HTTP endpoint]
14	local --> q2{Which client?}
15	remote --> q2
16	q2 --> claude_desktop[Claude Desktop]
17	q2 --> claude_code[Claude Code]
18	q2 --> cursor[Cursor]
19	q2 --> vscode[VS Code]
20	claude_desktop --> config[Generate config<br>+ test setup]
21	claude_code --> config
22	cursor --> config
23	vscode --> config
24	```
25
26	## Questions to Ask
27
28	### 1. Server Type
29	Ask: "Do you want to use the local or remote dbt MCP server?"
30
31	\| Local Server \| Remote Server \|
32	\| -------------------------------------------------------------------------------------------------------------------------------------------------------- \| ----------------------------------------------------------- \|
33	\| Runs on your machine via `uvx` \| Connects via HTTP to dbt platform \|
34	\| Required for development (authoring models, tests, docs) but can also connect to the dbt platform for consumption (querying metrics, exploring metadata) \| Best for consumption (querying metrics, exploring metadata) \|
35	\| Supports dbt CLI commands (run, build, test, show) \| No CLI commands (run, build, test) \|
36	\| Works without a dbt platform account but can also connect to the dbt platform for development (authoring models, tests, docs) \| Requires dbt platform account \|
37	\| No credit consumption \| Consumes dbt Copilot credits \|
38
39	### 2. MCP Client
40	Ask: "Which MCP client are you using?"
41	- Claude Desktop
42	- Claude Code (CLI)
43	- Cursor
44	- VS Code
45
46	### 3. Use Case (Local Server Only)
47	Ask: "What's your use case?"
48
49	\| CLI Only \| Platform Only \| Platform + CLI \|
50	\|----------\|---------------\|----------------\|
51	\| dbt Core/Fusion users \| dbt Cloud without local project \| Full access to both \|
52	\| No platform account needed \| OAuth or token auth \| Requires paths + credentials \|
53
54	### 4. Tools to Enable
55	Ask: "Which tools do you want enabled?" (show defaults)
56
57	\| Tool Category \| Default \| Environment Variable \|
58	\|---------------\|---------\|---------------------\|
59	\| dbt CLI (run, build, test, compile) \| Enabled \| `DISABLE_DBT_CLI=true` to disable \|
60	\| Semantic Layer (metrics, dimensions) \| Enabled \| `DISABLE_SEMANTIC_LAYER=true` to disable \|
61	\| Discovery API (models, lineage) \| Enabled \| `DISABLE_DISCOVERY=true` to disable \|
62	\| Admin API (jobs, runs) \| Enabled \| `DISABLE_ADMIN_API=true` to disable \|
63	\| SQL (text_to_sql, execute_sql) \| Disabled \| `DISABLE_SQL=false` to enable \|
64	\| Codegen (generate models/sources) \| Disabled \| `DISABLE_DBT_CODEGEN=false` to enable \|
65
66	## Prerequisites
67
68	### Local Server
69	1. Install `uv`: https://docs.astral.sh/uv/getting-started/installation/
70	2. Have a dbt project (for CLI commands)
71	3. Find paths:
72	- `DBT_PROJECT_DIR`: Folder containing `dbt_project.yml`
73	- macOS/Linux: `pwd` from project folder
74	- Windows: Full path with forward slashes (e.g., `C:/Users/name/project`)
75	- `DBT_PATH`: Path to dbt executable
76	- macOS/Linux: `which dbt`
77	- Windows: `where dbt`
78
79	### Remote Server
80	1. dbt Cloud account with AI features enabled
81	2. Production environment ID (from Orchestration page)
82	3. Personal access token or service token
83
84	See [How to Find Your Credentials](references/finding-credentials.md) for detailed guidance on obtaining tokens and IDs.
85
86	## Credential Security
87
88	- Always use environment variable references (e.g., `${DBT_TOKEN}`) instead of literal token values in configuration files that may be committed to version control
89	- Never log, display, or echo token values in terminal output
90	- When using `.en

People who liked this also viewed

6 picks

Type