Dbt
dbt MCP — manifest/run_results/sources/catalog parsing + DQ result tables…
- Pricing
- Open source
- Runs
- Locally
- Version
- 1.0.7
- Listing updated
- 4 days ago
About Dbt
Dbt is an open-source MCP server for databases. It runs locally on your machine and is started by your AI client.
dbt MCP — manifest/run_results/sources/catalog parsing + DQ result tables (BigQuery/Postgres)
Install
Run in a terminal
claude mcp add dbt --env DBT_PROJECT_DIR='<DBT_PROJECT_DIR>' --env PG_CONNECTION_STRING='<PG_CONNECTION_STRING>' -- npx -y @us-all/dbt-mcpAdd to claude_desktop_config.json
{
"mcpServers": {
"dbt": {
"command": "npx",
"args": [
"-y",
"@us-all/dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<DBT_PROJECT_DIR>",
"PG_CONNECTION_STRING": "<PG_CONNECTION_STRING>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"dbt": {
"command": "npx",
"args": [
"-y",
"@us-all/dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<DBT_PROJECT_DIR>",
"PG_CONNECTION_STRING": "<PG_CONNECTION_STRING>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"dbt": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@us-all/dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<DBT_PROJECT_DIR>",
"PG_CONNECTION_STRING": "<PG_CONNECTION_STRING>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"dbt": {
"command": "npx",
"args": [
"-y",
"@us-all/dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<DBT_PROJECT_DIR>",
"PG_CONNECTION_STRING": "<PG_CONNECTION_STRING>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"dbt": {
"command": "npx",
"args": [
"-y",
"@us-all/dbt-mcp"
],
"env": {
"DBT_PROJECT_DIR": "<DBT_PROJECT_DIR>",
"PG_CONNECTION_STRING": "<PG_CONNECTION_STRING>"
}
}
}
}Configuration
DBT_PROJECT_DIRPath to dbt project root (where dbt_project.yml lives).RequiredDBT_TARGET_DIRdbt target dir for manifest.json/run_results.json (default: $DBT_PROJECT_DIR/target).DBT_RUN_HISTORY_DIROptional dir for archived run_results.json history (glob-scanned).DQ_BACKENDDQ result table backend: 'bigquery' (default) or 'postgres'.DQ_RESULTS_TABLEFully qualified DQ checks table, e.g. 'project.data_ops.quality_checks'.DQ_SCORE_TABLEFully qualified DQ score-daily table, e.g. 'project.data_ops.quality_score_daily'.GOOGLE_APPLICATION_CREDENTIALSService account key path for BigQuery (ADC fallback supported).BQ_PROJECT_IDExplicit BigQuery project ID for DQ queries.PG_CONNECTION_STRINGPostgres connection string when DQ_BACKEND=postgres.DBT_ALLOW_WRITEReserved for future write tools. Default read-only.DQ_SCHEMADQ 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_ATOverride for the timestamp/date column on the DQ checks table. Default depends on DQ_SCHEMA preset.DQ_COL_CHECK_TYPEOverride for the check-type column on the DQ checks table. Default 'check_type'.DQ_COL_STATUSOverride for the status column on the DQ checks table. Default 'status'.DQ_COL_DATASETOverride for the dataset/source column on the DQ checks table. Default depends on preset.DQ_COL_TABLE_NAMEOverride for the table/target-name column on the DQ checks table. Default depends on preset.DQ_COL_SEVERITYOverride for the severity/dimension column on the DQ checks table. Default depends on preset.DQ_COL_FAILURE_COUNTOverride for the numeric failure-count column on the DQ checks table. Default depends on preset.DQ_COL_MESSAGEOverride for the message column on the DQ checks table. Default depends on preset.DQ_COL_CHECK_NAMEOverride 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_DATEOverride for the date column on the DQ score-daily table. Default depends on preset.DQ_COL_SCOPEOverride for the scope column on the DQ score-daily table. Set to 'none'/'null'/'-' if the table has no per-scope rollup.DQ_COL_TIEROverride for the tier column on the DQ score-daily table. Set to 'none'/'null'/'-' if the table has no tier dimension.DQ_TIER1_TARGET_PCTWhen 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_PATHOptional 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_TOOLSComma-separated category allowlist (dbt,quality,meta).DBT_DISABLEComma-separated category disablelist.
Pricing
Open source
Dbt FAQ
Is Dbt free?
Yes. Dbt is open source, so you can use and self-host it for free.
How do I add Dbt to Claude Code?
Run this command in your terminal: claude mcp add dbt --env DBT_PROJECT_DIR='<DBT_PROJECT_DIR>' --env PG_CONNECTION_STRING='<PG_CONNECTION_STRING>' -- npx -y @us-all/dbt-mcp
What are the best alternatives to Dbt?
The closest alternatives to Dbt are Midplane, PlatypusDB, Lorebase, Sovaria and model2data studio.
Alternatives to Dbt

Midplane
MCP serverPostgres gateway for AI agents with table grants, column masking and approval for writes
Runs locally- Open source
- 5 GitHub stars
- Databases

PlatypusDB
MCP serverGives MCP clients access to your PlatypusDB database connections, scoped per agent
Runs locally- Open source
- Databases

Lorebase
MCP serverLets agents read and change a governed, versioned Postgres knowledge graph
Runs locally- Open source
- Knowledge and memory
Sovaria
MCP serverManage a Sovaria backend (Postgres, auth, storage, functions) from an AI assistant
Not checked yet- 4 tools
- Remote
- Freemium
- Databases

model2data studio
MCP serverGenerate realistic connected test data, dbt projects and dashboards from a schema
- Remote
- Freemium
- Databases

semlayer
MCP serverInfers a semantic layer from your data warehouse and serves it to agents
Runs locally- Free
- Databases