MCP Observatory
github analyzed 6622aa4

dbt-labs/dbt-mcp

github

A MCP (Model Context Protocol) server for interacting with dbt.

maintainer
dbt-labs
license
Apache-2.0
first seen
2026-05-22
last seen
2026-06-17
releases · 30d
6
short id
risk 63/100 · heuristic grade
D high
  • vulnerabilitiesattested+11
  • capability exposureinferred+35
  • tool safetyinferred+25
  • trust mitigatorsmixed−8

attestedinferredmixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 10m ago · see ecosystem CVEs →

capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 3 CVEs · grade factor +11
LOW
All MCP Tool Arguments Including Raw SQL and --vars Credentials Transmitted to dbt Labs Telemetry by… EPSS 0% CVE-2026-44970 affects ["<= 1.17.0"]
LOW
Tool Arguments Including SQL Queries and Credentials Logged in Plaintext Without Redaction When File… EPSS 0% CVE-2026-44969 affects ["<= 1.17.0"]
MEDIUM
Argument Injection in dbt CLI Tool Wrappers via node_selection and resource_type Parameters EPSS 0% CVE-2026-44968 affects ["<= 1.17.0"]
tool safety 3 findings · grade factor +25
  1. highexfiltration comboget_product_doc_pages

    single tool reads + sends: fs, net

  2. hightool shadowingexecute_sql

    tool "execute_sql" shadows a verified server's tool

    shadows greptimeteam/greptimedb-mcp-server

  3. lowexfiltration combosearch_product_docs

    single tool reads + sends: net, db

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 6622aa4 · analyzer v18 · 10h ago

skills & prompt files 3

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:dbt-labs/dbt-mcp/badge.svg)](https://mcpobservatory.com/servers/github:dbt-labs/dbt-mcp/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of dbt-labs.