DBT_PROJECT_DIR — Path to dbt project root (where dbt_project.yml lives).
DBT_TARGET_DIR — dbt target dir for manifest.json/run_results.json (default: $DBT_PROJECT_DIR/target).
DBT_RUN_HISTORY_DIR — Optional dir for archived run_results.json history (glob-scanned).
DQ_BACKEND — DQ result table backend: 'bigquery' (default) or 'postgres'.
DQ_RESULTS_TABLE — Fully qualified DQ checks table, e.g. 'project.data_ops.quality_checks'.
DQ_SCORE_TABLE — Fully qualified DQ score-daily table, e.g. 'project.data_ops.quality_score_daily'.
GOOGLE_APPLICATION_CREDENTIALS — Service account key path for BigQuery (ADC fallback supported).
BQ_PROJECT_ID — Explicit BigQuery project ID for DQ queries.
PG_CONNECTION_STRING — Postgres connection string when DQ_BACKEND=postgres.
DBT_ALLOW_WRITE — Reserved for future write tools. Default read-only.
DQ_SCHEMA — DQ result-table schema preset: 'generic' (default) or 'us-all'. Use DQ_COL_* env vars to override individual columns on top of the preset.
DQ_COL_RUN_AT — Override for the timestamp/date column on the DQ checks table. Default depends on DQ_SCHEMA preset.
DQ_COL_CHECK_TYPE — Override for the check-type column on the DQ checks table. Default 'check_type'.
DQ_COL_STATUS — Override for the status column on the DQ checks table. Default 'status'.
DQ_COL_DATASET — Override for the dataset/source column on the DQ checks table. Default depends on preset.
DQ_COL_TABLE_NAME — Override for the table/target-name column on the DQ checks table. Default depends on preset.
DQ_COL_SEVERITY — Override for the severity/dimension column on the DQ checks table. Default depends on preset.
DQ_COL_FAILURE_COUNT — Override for the numeric failure-count column on the DQ checks table. Default depends on preset.
DQ_COL_MESSAGE — Override for the message column on the DQ checks table. Default depends on preset.
DQ_COL_CHECK_NAME — Override for the check_name column on the DQ checks table. Set to 'none'/'null'/'-' to synthesize check_name from check_type and table_name.
DQ_COL_SCORE_DATE — Override for the date column on the DQ score-daily table. Default depends on preset.
DQ_COL_SCOPE — Override for the scope column on the DQ score-daily table. Set to 'none'/'null'/'-' if the table has no per-scope rollup.
DQ_COL_TIER — Override for the tier column on the DQ score-daily table. Set to 'none'/'null'/'-' if the table has no tier dimension.
DQ_TIER1_TARGET_PCT — When no tier column is configured (us-all preset or DQ_COL_TIER=none), the overall_score threshold dq-tier-status compares against (default 99.5). Superseded by DBT_SLA_CONFIG_PATH tier_sla.1 if both are set.
DBT_SLA_CONFIG_PATH — Optional path to a YAML file that defines tier_sla (per-tier overall_score targets) and dbt_sla (test/freshness pass rates). When set, dq-tier-status and dq-tier-by-source read tier targets from this file, and dbt-sla-status compares run_results / sources pass rates against dbt_sla.test_pass_pct / freshness_pass_pct. Mtime cached.
dbt MCP server — manifest.json, run_results.json, sources.json, catalog.json, plus DQ result tables (BigQuery / Postgres) behind one stdio MCP. Built on @us-all/mcp-toolkit.
A read-only window into your dbt project for LLM clients. No dbt run triggering — just deep introspection, run-history analysis, source freshness, per-column test coverage, lineage walks, and (if you have a custom DQ result table) historical check trends and Tier SLA status.
dbt MCP — manifest/run_results/sources/catalog parsing + DQ result tables (BigQuery/Postgres)
รันบน PlugMCP
Host a copy with our keys and logs.
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
For DAG triggering / run history / log tails, install the companion @us-all/airflow-mcp alongside.
27 tools across 3 categories (dbt, quality, meta) — 21 primitive tools + 5 aggregations + 1 meta
4 MCP Prompts for triage workflows
5 aggregation tools that replace 3-5 round-trips of "list / get / list"
extractFields response projection on high-volume reads
Read-only by default
Hybrid backend: BigQuery (default) or Postgres for DQ result tables — both peer-imported lazily
Install
# 1. add the MCP server
pnpm add -D @us-all/dbt-mcp
# 2. add the DQ backend you actually use (only if you query custom DQ tables):
pnpm add -D @google-cloud/bigquery # OR
pnpm add -D pg
The server speaks MCP stdio; wire it into Claude Desktop / Cursor / any MCP client. Set MCP_TRANSPORT=http to opt in to Streamable HTTP transport (Bearer auth, /health endpoint).
In this flavor quality_score_daily is one row per day (no per-scope rollup, no tier column). dq-tier-status falls back to comparing the day's overall_score against DQ_TIER1_TARGET_PCT (default 99.5).
dq-get-check-history requires checkName formatted as '<check_type>:<target_name>' since us-all has no native check_name column.
Per-column overrides — DQ_COL_*
If your DQ tables don't match either preset, layer per-column overrides on top of DQ_SCHEMA. Any DQ_COL_* env var, when set, replaces the preset value for that single column. Unset vars keep the preset default.
Overrides are validated as simple SQL identifiers to avoid injecting raw SQL through environment variables. Table names in DQ_RESULTS_TABLE / DQ_SCORE_TABLE are also validated and quoted for the configured backend.
Env var
Logical concept
Generic preset
us-all preset
DQ_COL_RUN_AT
timestamp/date on the checks table
run_at
run_date
DQ_COL_CHECK_TYPE
check type / dimension family
check_type
check_type
DQ_COL_STATUS
pass/fail/warn/error
status
status
DQ_COL_DATASET
dataset / source / schema
dataset
source
DQ_COL_TABLE_NAME
table or target name
table_name
target_name
DQ_COL_SEVERITY
severity / dimension
severity
dimension
DQ_COL_FAILURE_COUNT
numeric failure count / metric
failure_count
metric_value
DQ_COL_MESSAGE
free-text or JSON message
message
details::text
DQ_COL_CHECK_NAME
natural identifier of the check
check_name
(none)
DQ_COL_SCORE_DATE
date column on the score table
score_date
run_date
DQ_COL_SCOPE
scope/tenant column on score table
scope
(none)
DQ_COL_TIER
tier column on score table
tier
(none)
For the three nullable columns (DQ_COL_CHECK_NAME, DQ_COL_SCOPE, DQ_COL_TIER), set the value to none / null / - to declare "no native column":
Without check_name → the tools synthesize one from check_type || ':' || table_name. dq-get-check-history then expects checkName formatted as '<check_type>:<table_name>'.
Without scope → dq-score-trend's scope filter is ignored (with a caveat) and dq-tier-status switches to the single-overall_score path that compares against DQ_TIER1_TARGET_PCT.
Without tier → same single-overall_score fallback.
Example — generic preset against a Postgres schema where columns happen to be named differently:
DQ_SCHEMA=generic
DQ_COL_RUN_AT=checked_at
DQ_COL_DATASET=schema_name
DQ_COL_TABLE_NAME=tbl
DQ_COL_FAILURE_COUNT=fail_n
DQ_COL_CHECK_NAME=none # synthesize from check_type+tbl
DQ_COL_SCOPE=none # no per-team rollup
DQ_COL_TIER=none # use DQ_TIER1_TARGET_PCT instead
SLA config (optional) — DBT_SLA_CONFIG_PATH
Set DBT_SLA_CONFIG_PATH to a YAML file to surface project-defined tier targets and DBT SLAs to the quality tools. Schema (extra keys ignored):
dq-tier-status — per-tier rollup compares each row's overall_score against the matching target. Without this file, hardcoded {1: 99.5, 2: 99.0, 3: 95.0} is used.
dq-tier-by-source — per-source pass-rate is compared to the target for that source's tier (resolved from dbt sources.yml meta.tier).
dq-tier-status no-tier-column path (us-all preset / DQ_COL_TIER=none) — uses tier_sla.1 as the single target. DQ_TIER1_TARGET_PCT env still works as a fallback when no SLA file is set.
The dbt_sla block drives:
dbt-sla-status — computes test pass rate from latest run_results.json and freshness pass rate from sources.json, then compares each axis against dbt_sla.test_pass_pct / dbt_sla.freshness_pass_pct. Returns passPct, target, meeting per axis plus caveats when fields or artifacts are missing.
The file is mtime-cached; edits between tool calls are picked up automatically.
Per-tier rollup from quality_checks — dq-tier-by-source
For schemas where quality_score_daily has only one row per day (no per-scope/tier breakdown), dq-tier-by-source reconstructs a per-tier picture from the raw quality_checks rows. Two modes:
mode: "source" (default) — group by source/dataset column
Use when each row of quality_checks represents a check on a source group and the dataset/source column carries the dbt source-group name directly.
Builds a source_name -> tier map from the dbt manifest's sources.<source>.<table>.meta.tier (first table's tier per source group).
Groups quality_checks rows by the dataset/source column and computes pass rate per source over a date or sinceHours window.
Looks up each source's tier and target (from SLA config or defaults), reports meeting / missing per tier.
mode: "table" — group by table_name column
Use when the dataset/source column is a category (bq / dbt / airflow) and the actual dbt source-table identifier lives in the table_name / target_name column as <source_group>.<table>. Common in checks tables that consolidate signals from heterogeneous backends.
Builds a <source_group>.<table> -> tier map from the manifest using each source entry's source_name + name + meta.tier — picks up table-level tier overrides naturally.
Groups quality_checks rows by the table_name column. Pre-filter via sourceFilter (e.g. sourceFilter: "bq") when only some categories produce parseable target names.
Each rollup key is parsed as <source_group>.<table>; rows without a . or whose key is not in the manifest land in caveats[].
Untiered rows (no manifest meta.tier) and unparseable rows always appear in caveats[] so you can tier them or accept the gap.
Tested-against schemas
dbt manifest schema v11 / v12 — the current top version. dbt 1.7 emits v11; dbt 1.8 through 1.12 all emit v12 (the schema evolves additively in-place). Newer/unknown versions still parse, but a caveats line will flag them.
Companion server
For Airflow DAG operations (list, runs, task instances, log tail, trigger, clear), install @us-all/airflow-mcp alongside this server.
Build
pnpm install
pnpm run build # tsc → dist/
pnpm test # vitest
pnpm run smoke # spawns dist/index.js, calls initialize + tools/list (set env first)