MCP, MCP server
Dbt Mcp
A MCP (Model Context Protocol) server for interacting with dbt.
Compatibility: Not stated.
Grade C
One Medium finding. Read the findings before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 3365e6dd75d1.
INSTALL_REMOTE_SCRIPT
Why this grade
- INSTALL_REMOTE_SCRIPT Medium
Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).
.github/workflows/run-checks-pr.yaml, line 78
run: curl -fsSL https://d2lang.com/install.sh | sh -s -- --version v0.9.0
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
examples/aws_strands_agent/dbt_data_scientist/tools/dbt_compile.py, line 36
proc = subprocess.run(
examples/aws_strands_agent/dbt_data_scientist/tools/dbt_model_analyzer.py, line 152
result = subprocess.run(
examples/aws_strands_agent/dbt_data_scientist/tools/dbt_model_analyzer.py, line 168
result = subprocess.run(
Show more
examples/aws_strands_agent/dbt_data_scientist/tools/dbt_model_analyzer.py, line 184
result = subprocess.run(
src/dbt_mcp/dbt_cli/binary_type.py, line 30
result = subprocess.run(
src/dbt_mcp/dbt_cli/binary_type.py, line 75
result = subprocess.run(
src/dbt_mcp/dbt_cli/tools.py, line 132
process = subprocess.Popen(
src/dbt_mcp/dbt_codegen/tools.py, line 48
process = subprocess.Popen(
Install and update
Serious
install fetches a script from the network.
INSTALL_REMOTE_SCRIPT
.github/workflows/run-checks-pr.yaml, line 78
run: curl -fsSL https://d2lang.com/install.sh | sh -s -- --version v0.9.0
Network
Concern
can reach a host that is not written as a fixed address.
NETWORK_NO_FIXED_HOST
ui/src/App.tsx, line 72
const response = await fetch(input, {
ui/src/main.tsx, line 24
fetch(url, { method: "POST", keepalive: true }).catch(() => {});
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
examples/ai_sdk_agent/src/index.ts, line 14
const token = process.env.DBT_TOKEN;
examples/aws_strands_agent/dbt_data_scientist/quick_mcp_test.py, line 19
token = os.environ.get("DBT_TOKEN")
examples/aws_strands_agent/dbt_data_scientist/tools/dbt_mcp.py, line 16
DBT_TOKEN = os.environ.get("DBT_TOKEN")
Show more
examples/google_adk_agent/main.py, line 17
if not os.environ.get("GOOGLE_GENAI_API_KEY"):
examples/langgraph_agent/main.py, line 37
"Authorization": f"token {os.environ.get('DBT_TOKEN')}",
examples/openai_agent/main_streamable.py, line 48
token = os.environ.get("DBT_TOKEN")
examples/openai_responses/main.py, line 11
token = os.environ.get("DBT_TOKEN")
examples/pydantic_ai_agent/main.py, line 14
token = os.environ.get("DBT_TOKEN")
examples/ag2_agent/main_stdio.py, line 6
Run from the repo root so the .env file is discovered:
examples/ag2_agent/main_stdio.py, line 9
The .env file should be configured as described in the root README.
examples/ag2_agent/main_stdio.py, line 28
args=["--env-file", str(dbt_mcp_dir / ".env"), "dbt-mcp"],
examples/aws_strands_agent/dbt_data_scientist/tools/dbt_compile.py, line 26
# Load environment variables from .env file
examples/aws_strands_agent/dbt_data_scientist/tools/dbt_mcp.py, line 130
print("Please set these in your .env file or environment.")
examples/crewai_agent/main.py, line 11
args=["--env-file", f"{dbt_mcp_dir}/.env", "dbt-mcp"],
examples/google_adk_agent/main.py, line 28
args=["--env-file", f"{dbt_mcp_dir}/.env", "dbt-mcp"],
examples/openai_agent/main.py, line 20
f"{dbt_mcp_dir}/.env",
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Note
a file was over the read cap and was not fully read. the file cap was reached before every file was read.
OBFUSCATION_FILE_OVER_READ_CAP OBFUSCATION_FILE_CAP_REACHED
uv.lock, line 1
version = 1
examples/crewai_agent/uv.lock, line 1
version = 1
examples/langgraph_agent/uv.lock, line 1
version = 1
Show more
tests/unit/mcp/test_http_proxy_sessions.py, line 1
import asyncio
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 3365e6dd75d1. requests shell access. The manifest names this permission. install fetches a script from the network. can reach a host that is not written as a fixed address. reads a credential or environment file. a file was over the read cap and was not fully read. the file cap was reached before every file was read.
Date and source
Date checked:
github.com
Commit graded: 3365e6dd75d1bb4ff92cceb25da6d1a59454b002
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.