Warehouse MCP Server

What the code does

We read the source, 21 h ago · rules 3dff92dd89df

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

RUN apt-get update \
 && apt-get install -y --no-install-recommends python3 make g++ ca-certificates \

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

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 warehouse-mcp -- npx -y warehouse-mcp

{
  "mcpServers": {
    "warehouse-mcp": {
      "args": [
        "-y",
        "warehouse-mcp"
      ],
      "command": "npx"
    }
  }
}

[mcp_servers.warehouse-mcp]
command = "npx"
args = ["-y", "warehouse-mcp"]

{
  "mcpServers": {
    "warehouse-mcp": {
      "args": [
        "-y",
        "warehouse-mcp"
      ],
      "command": "npx"
    }
  }
}

{
  "mcpServers": {
    "warehouse-mcp": {
      "args": [
        "-y",
        "warehouse-mcp"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: MCP_TRANSPORT (Set to 'stdio' for desktop AI clients (Claude Desktop, Cursor). Defaults to 'http'.), WAREHOUSE_TYPE (Which warehouse to connect to. One of: postgres, oracle, redshift, snowflake, bigquery, duckdb. (DuckDB also handles MotherDuck via DUCKDB_PATH=md:<db>.)), MCP_API_KEYS (Comma-separated bearer keys with role and optional warehouse-role impersonation: 'key1:reader,key2:admin', 'key3:reader:set_role=alice'. Leave empty for stdio (OS process boundary is the trust boundary). Required for HTTP.), DUCKDB_PATH (DuckDB file path, ':memory:', or 'md:<database>' for MotherDuck. Required when WAREHOUSE_TYPE=duckdb.), MOTHERDUCK_TOKEN (MotherDuck service token. Required when DUCKDB_PATH starts with 'md:'.), PG_HOST (Postgres host. Required when WAREHOUSE_TYPE=postgres. (Use REDSHIFT_HOST for Redshift.)), PG_DATABASE (Postgres database name.), PG_USER (Postgres user.), PG_PASSWORD (Postgres password.), ORACLE_USER (Oracle user. Required when WAREHOUSE_TYPE=oracle.), ORACLE_PASSWORD (Oracle password.), ORACLE_CONNECT_STRING (Oracle Easy Connect (e.g. host:1521/SERVICE), TNS descriptor, or alias.), SNOWFLAKE_ACCOUNT (Snowflake account identifier (e.g. xy12345.us-east-1). Required when WAREHOUSE_TYPE=snowflake.), SNOWFLAKE_USER (Snowflake username.), SNOWFLAKE_PRIVATE_KEY_PATH (Path to PKCS8 private key (.p8). Snowflake auth is key-pair only; password auth is not supported.), BIGQUERY_PROJECT (GCP project id. Required when WAREHOUSE_TYPE=bigquery.), GOOGLE_APPLICATION_CREDENTIALS (Path to BigQuery service-account JSON. Omit on GKE / Cloud Run with workload identity.), GUARDRAIL_PII_MASK (Set to 'on' to enable role-aware PII masking on result rows (emails, SSNs, phones, IPs, Luhn-validated CCs). Off by default.), MCP_RATE_LIMIT_RPM (Per-principal token-bucket rate limit on tool invocations. 0 = disabled. Recommend 60 for production.). The author declared them in the registry entry; get the values from the project itself.