--- title: "dbt MCP Server: review, setup & limitations · Undominated.ai" canonical: https://undominated.ai/mcp-servers/dbt/ description: "Connects dbt project metadata and lineage with optional local CLI, Semantic Layer and Platform operations." --- # dbt MCP Server: review, setup & limitations · Undominated.ai > Connects dbt project metadata and lineage with optional local CLI, Semantic Layer and Platform operations. [← Explore all mcp servers](/mcp-servers/) ANALYTICS ENGINEERING / dbt Labs # dbt MCP Server Connects dbt project metadata and lineage with optional local CLI, Semantic Layer and Platform operations. See setup guidance ↓Original source ↗ SOURCE REVIEW Reviewed 2026-09-21 Evidence 6 linked sources Publisher dbt Labs Licence Apache-2.0 ↗ Revision e0b8c67f9a66 Read what was—and wasn’t—checked ↓ “This MCP (Model Context Protocol) server provides various tools to interact with dbt.” dbt Labs · upstream description ↗ Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - Supports both project understanding and concrete build/test/job workflows. - The configuration distinguishes discovery, local CLI, semantic and administrative tool groups. ### A good fit for - Tracing a dbt model’s lineage and test failures before changing a transformation. ### Weigh up before choosing - CLI and administrative tools can change warehouse objects or trigger/cancel jobs. - Platform features require the relevant credentials and entitlements; project metadata access alone does not enable them. - Platform execute_sql requires a personal access token; a service token does not enable it. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - README.md (installation, capability and permission sections) - pyproject.toml - src/dbt_mcp/main.py - src/dbt_mcp/config/settings.py - LICENSE - Official local MCP setup: launch command, toolset requirements and authentication table ### Our findings - The README explicitly warns that CLI tools may modify data models, sources and warehouse objects. - Settings provide allow/deny lists; an unset enable list means all configured tools rather than no tools. - The current setup guide says missing required settings automatically disable the corresponding toolsets. ### Not established by this review - Server startup, authentication and tool execution were not tested. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Connect a server deliberately. Upstream setup instructions ↗ DOCUMENTED COMMAND uvx dbt-mcp Copy command ↗ Copying does not execute this command. It may retrieve a newer version than the reviewed source. - Use uvx dbt-mcp in the client configuration; set DBT_PROJECT_DIR and DBT_PATH for local CLI tools, or configure the documented Platform authentication. - Provide the local project/runtime or the relevant dbt Platform credentials according to the selected mode. ### Before you start - A supported Python environment and dbt project/runtime or Platform account. ### Compatibility An MCP client supporting stdio. · A supported Python environment and dbt project/runtime or Platform account. ### Implementation Python ### Transports stdio ### Analytics engineering / Configured credentials or local access - Reads model definitions, lineage and metrics; enabled CLI/API tools can build models, execute queries and manage job runs. ### Cost model dbt Platform entitlements, warehouse queries and local execution determine cost. 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - Official documentation ↗ Checked 2026-09-21 https://github.com/dbt-labs/dbt-mcp/blob/e0b8c67f9a661c5414977301cd1b05ea7b2e6fc9/README.md Supports: summary, whySelected, bestFor, limitations, install, access, compatibility, transports - Applicable source licence ↗ Checked 2026-09-21 https://github.com/dbt-labs/dbt-mcp/blob/e0b8c67f9a661c5414977301cd1b05ea7b2e6fc9/LICENSE Supports: license - Implementation: pyproject.toml ↗ Checked 2026-09-21 https://github.com/dbt-labs/dbt-mcp/blob/e0b8c67f9a661c5414977301cd1b05ea7b2e6fc9/pyproject.toml Supports: language, review - Implementation: src/dbt_mcp/main.py ↗ Checked 2026-09-21 https://github.com/dbt-labs/dbt-mcp/blob/e0b8c67f9a661c5414977301cd1b05ea7b2e6fc9/src/dbt_mcp/main.py Supports: language, review - Implementation: src/dbt_mcp/config/settings.py ↗ Checked 2026-09-21 https://github.com/dbt-labs/dbt-mcp/blob/e0b8c67f9a661c5414977301cd1b05ea7b2e6fc9/src/dbt_mcp/config/settings.py Supports: language, review - dbt local MCP setup ↗ Checked 2026-09-21 https://docs.getdbt.com/docs/dbt-ai/setup-local-mcp Supports: install, limitations, access, review KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### AWS IaC MCP Server ↗ Validates CloudFormation templates, retrieves CDK/CloudFormation guidance and investigates failed deployments.](/mcp-servers/aws-iac/)[### Chroma MCP ↗ Lets an assistant create and query Chroma collections through local, HTTP or Chroma Cloud database connections.](/mcp-servers/chroma/)[### ClickHouse MCP Server ↗ Queries ClickHouse and inspects table metadata, with read-only SQL by default and separate authentication for network transports.](/mcp-servers/clickhouse/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)