Dbt runs on your own machine — the client starts it, so there is no endpoint to ping. 60 installs a week from npm. Last commit 10 Jul 2026.
dbt MCP — manifest/run_results/sources/catalog parsing + DQ result tables (BigQuery/Postgres)
Today is the operative word: we check Dbt every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add dbt -- npx -y @us-all/dbt-mcp
{
"mcpServers": {
"dbt": {
"args": [
"-y",
"@us-all/dbt-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.dbt]
command = "npx"
args = ["-y", "@us-all/dbt-mcp"]
{
"mcpServers": {
"dbt": {
"args": [
"-y",
"@us-all/dbt-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"dbt": {
"args": [
"-y",
"@us-all/dbt-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
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_TOOLS (Comma-separated category allowlist (dbt,quality,meta).), DBT_DISABLE (Comma-separated category disablelist.).
The author declared them in the registry entry; get the values from the project itself.
MCP server for querying PostgreSQL databases
MCP server for Databricks, BigQuery, PostgreSQL, MySQL, SQL Server, SQLite, MariaDB
Production MCP server for Postgres, Oracle, Snowflake, BigQuery, Redshift, DuckDB, MotherDuck.
Production-grade PostgreSQL MCP server — 254 tools for query, tuning & ops, read-only by default.
MCP server for managing Prisma Postgres.
PostgreSQL MCP — query databases, inspect schemas, explain queries.
MCP server for PostgreSQL. Read-only by default, row caps, timeouts, secrets never logged.
Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.
Answers built from our own checks of this server.