Publisher · GitHub organization

dbt-labs

github.com/dbt-labs ↗Last audit 28 Oct 2026

dbt-labs publishes 1 MCP server and 10 agent skills on the atlas: 6 SAFE, 3 CAUTION, 2 BLOCK, with a mean score of 83/100. Every listing below is audited on its own.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “dbt-labs: skills and MCP servers”. Retrieved 28 Oct 2026. https://modelsatlas.com/orgs/dbt-labs
Listings
11

1 MCP servers · 10 skills

Mean score
83 / 100

mean of the audit scores

Findings
30

across all listings

Stars
8.1K

on the listed repositories

✓SAFE 6!CAUTION 3✕BLOCK 2

Everything dbt-labs publishes here

Most stars first · stamps show the audited version

running-dbt-commandsdbt-labs/dbt-agent-skills
Skill ★ 747
✓SAFEB · 89 · 26 Oct 2026
working-with-dbt-meshdbt-labs/dbt-agent-skills
Skill ★ 747
✓SAFEB · 89 · 28 Oct 2026
using-dbt-for-analytics-engineeringdbt-labs/dbt-agent-skills
Skill ★ 747
!CAUTIONC · 79 · 28 Oct 2026
troubleshooting-dbt-job-errorsdbt-labs/dbt-agent-skills
Skill ★ 747
✕BLOCKD · 69 · 27 Oct 2026
fetching-dbt-docsdbt-labs/dbt-agent-skills
Skill ★ 746
!CAUTIONC · 79 · 24 Oct 2026
migrating-dbt-core-to-fusiondbt-labs/dbt-agent-skills
Skill ★ 746
✕BLOCKD · 69 · 26 Oct 2026
configuring-dbt-mcp-serverdbt-labs/dbt-agent-skills
Skill ★ 745
✓SAFEB · 89 · 23 Oct 2026
building-dbt-semantic-layerdbt-labs/dbt-agent-skills
Skill ★ 745
!CAUTIONC · 79 · 22 Oct 2026
Skill ★ 744
✓SAFEB · 89 · 21 Oct 2026
adding-dbt-unit-testdbt-labs/dbt-agent-skills
Skill ★ 742
✓SAFEB · 89 · 20 Oct 2026
dbtdbt-labs/dbt-mcp
MCP ★ 608
✓SAFEB · 89 · 29 Sep 2026

Questions

Are dbt-labs's MCP servers and skills safe to install?
Of 11 listings, 6 are SAFE, 3 CAUTION and 2 BLOCK, with a mean score of 83 out of 100. That is an average over separate audits: check each listing's own stamp before installing.
What does this page tell me about dbt-labs?
It collects every skill and MCP server on the atlas whose source lives under github.com/dbt-labs, with each one's verdict. It says nothing about who runs the organisation, and publisher identity is not verified here.
Can a publisher change its verdicts?
No. Each verdict comes from reading the source at a named commit. If a finding is wrong, report it with your reasoning on the listing's page and it is re-audited; the correction is public.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.