{"id":"niclasolofsson-dbt-core-mcp","name":"dbt-core-mcp","af_score":53.2,"security_score":27.5,"reliability_score":35.0,"what_it_does":"A Model Context Protocol (MCP) server that lets AI assistants interact with dbt projects: inspect project/resource metadata (models, sources, seeds, snapshots, tests), analyze lineage and impact, and run dbt commands/queries using the user’s existing dbt/adapter/environment via “bridge execution” (no dbt-core/adapters required on the server).","best_when":"You have a local dbt project and want an agent to safely operate within your environment (workspace directory, dbt version, adapter, and credentials) to inspect metadata and execute dbt commands.","avoid_when":"You cannot grant the agent permission to run dbt commands against your data warehouses (or you require strict restrictions on execution). Also avoid if your dbt project relies heavily on Python models.","last_evaluated":"2026-03-30T15:42:07.346349+00:00","has_mcp":true,"has_api":false,"auth_methods":["No explicit auth mechanism described for the MCP server itself; uses the user’s local dbt configuration/credentials to connect to the target warehouse during dbt execution."],"has_free_tier":false,"known_gotchas":["Executing dbt commands can be long-running and can fail due to warehouse/adapter/auth/profile issues; the server mentions optional timeouts for dbt commands.","Only SQL models are supported; Python models are not.","The tool may trigger dbt compile when requesting compiled SQL (can be expensive/time-consuming and may require access to your project and dependencies)."],"error_quality":0.0}