dbt’s remote MCP server can query metrics through the Semantic Layer, inspect model metadata, and run SQL for dbt Cloud projects. Register it in TrueFoundry with the required dbt token and environment headers.Documentation Index
Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt
Use this file to discover all available pages before exploring further.
Prerequisites
- A dbt Cloud account on Starter, Team, or Enterprise.
- Account Admin access in dbt Cloud.
- A production environment and, if you need
execute_sql, a development environment. - dbt AI features enabled for the account.
Create a dbt Token
Use a Personal Access Token for individual access or when you needexecute_sql. Use a service token for shared read access. Copy the token immediately after creation.
Collect Required IDs
Find the numeric IDs from dbt Cloud URLs:| Header | Value |
|---|---|
x-dbt-prod-environment-id | Production environment ID |
x-dbt-dev-environment-id | Development environment ID for SQL and Fusion tools |
x-dbt-user-id | User ID for SQL and Fusion tools |
Register in TrueFoundry
Use the standard dbt MCP URL:https://abc123.us1.dbt.com/api/ai/v1/mcp/.
Add it as a remote MCP server in TrueFoundry with bearer-token authentication. Configure the dbt token and the required x-dbt-* headers. If needed, add optional headers such as x-dbt-disable-toolsets or x-dbt-disable-tools to hide risky tools.
Security Notes
PATs inherit the user’s permissions, while service tokens use assigned permission sets. Rotate tokens regularly and disableexecute_sql unless agents need direct SQL execution.