dbt-mcp-server CLAUDE.md

dbt-mcp-server CLAUDE.md is an instructions file for Claude Code from us-all/dbt-mcp-server. It costs 2,273 tokens per session, scanned A, original, MIT.

Repository instructions for a read-only dbt data-quality MCP server. dbt is a tool that builds and documents data transformations, and MCP lets an agent access defined tools.

In plain words
What is it for?
Use them when developing or maintaining the server that exposes dbt metadata and data-quality results from BigQuery or PostgreSQL.
Why use it?
They explain the project structure, supported dbt artifacts, databases, configuration, and validation requirements before making changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/us-all/dbt-mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/us-all/dbt-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dbt-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/us-all/dbt-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/us-all/dbt-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/us-all/dbt-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/us-all/dbt-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,273 This file is loaded in full into every session.
When invoked 2,273 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02273 $0.02273
Opus 5 $0.01137 $0.01137
Sonnet 5 $0.00455 $0.00455
Haiku 4.5 $0.00227 $0.00227

Measured 5d ago against content hash 3b6b9df92347, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dbt-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

이 파일은 Claude Code가 이 저장소에서 작업할 때 참고하는 컨텍스트입니다.

프로젝트 개요

@us-all/dbt-mcp — dbt artifacts(manifest.json/run_results.json/sources.json/catalog.json) + 사용자 DQ 결과 테이블(BQ/PG)을 노출하는 stdio MCP. 27 도구 (21 primitive + 5 aggregations + 1 meta) + 4 Prompts. 전부 read-only.

  • 타겟 dbt: 1.7+ (manifest schema v11/v12 검증 — schemas.getdbt.com 최상단이 v12, v13+ 미존재. 1.7=v11, 1.8~1.12=v12. 신/미지 버전은 lenient 파싱 + caveat)
  • DQ 백엔드: BigQuery 기본 + Postgres 옵션, 둘 다 lazy peer import
  • Airflow는 별도 서버: @us-all/airflow-mcp
  • 표준: @us-all MCP Standard 준수

최근 변경사항

  • v1.0.7 (2026-06-19): MCP tool annotations 적용 — @us-all/mcp-toolkit ^1.3.0inferToolAnnotations를 중앙 tool() 헬퍼에 추가, 전 도구에 readOnlyHint/destructiveHint/openWorldHint 자동 부여 (override 0). 비파괴 패치. 54/54 test.

디렉토리

src/
├── index.ts                   # 카테고리별 tool() 등록 + Prompts
├── config.ts                  # ENV 로딩 + 검증 (DBT/DQ 2 블록)
├── tool-registry.ts           # CATEGORIES = dbt / quality / meta
├── clients/
│   ├── dbt-artifacts.ts       # manifest/run_results/sources/catalog 로더 + mtime cache + run history walk
│   └── dq-store.ts            # BQ/PG 듀얼 백엔드 lazy import + ?-style placeholder rewrite
├── tools/
│   ├── utils.ts               # wrapToolHandler + WriteBlocked / ConfigMissing / DqStore 에러 클래스
│   ├── dbt-models.ts          # dbt-list-models, dbt-get-model, dbt-graph, dbt-coverage (4)
│   ├── dbt-tests.ts           # dbt-list-tests, dbt-get-test (2)
│   ├── dbt-sources.ts         # dbt-list-sources, dbt-get-source, dbt-list-exposures (3)
│   ├── dbt-macros.ts          # dbt-list-macros, dbt-get-macro (2)
│   ├── dbt-runs.ts            # dbt-list-runs, dbt-get-run-results, dbt-failed-tests, dbt-slow-models (4)
│   ├── quality-results.ts     # dq-list-checks, dq-get-check-history, dq-failed-checks-by-dataset (3)
│   ├── quality-scores.ts      # dq-score-trend, dq-tier-status, dq-tier-by-source (3) — Tier SLA 비교 + source.meta.tier 롤업
│   └── aggregations.ts        # failed-tests-summary, freshness-status, dq-score-snapshot, incident-context, dbt-sla-status (5)
└── prompts/
    └── index.ts               # 4 Prompts

tests/
├── fixtures/                  # 작은 manifest.json / run_results.json / sources.json
├── dbt-models.test.ts         # 6
├── dbt-tests-and-macros.test.ts # 5
├── dbt-sources.test.ts        # 3
├── dbt-runs.test.ts           # 4
└── dq-store.test.ts           # 3 (driver 주입)

Read the full file on GitHub · 111 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 111 lines · 2,273 tokens per session scan A 3b6b9df92347

Subscribe to this mod's changes

dbt-mcp-server CLAUDE.md is an instructions file published in the GitHub repository us-all/dbt-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,273 tokens to every session, about $0.0114 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.