dbt Cloud MCP server
Remote MCP server for dbt Cloud AI features including Semantic Layer, SQL, and Discovery tools Connect your AI agents to dbt Cloud with enterprise-grade governance, observability, and control through Mintive Gateway.
Tools included with dbt Cloud MCP
get_mart_models
Get the name and description of all mart models in the environment. A mart model is part of the presentation layer of...
get_all_models
Get the name and description of all dbt models in the environment.
get_model_details
Retrieves information about a specific dbt model, including compiled SQL, description, database, schema, alias, and c...
get_model_parents
Retrieves the parent models of a specific dbt model. These are the models that the specified model depends on. You c...
get_model_children
Retrieves the child models (downstream dependencies) of a specific dbt model. These are the models that depend on the...
get_model_health
Retrieves information about the health of a dbt model, including the last time it ran, the last test execution status...
get_exposures
Get the id, name, description, and url of all exposures in the dbt environment. Exposures represent downstream applic...
get_exposure_details
Get detailed information about one or more exposures by name or unique IDs. Parameters: - unique_id (optional): ID o...
get_all_sources
Get the name, description, and metadata of all dbt sources in the environment. Sources represent external data tables...
get_source_details
Retrieves detailed information about a specific dbt source, including database, schema, identifier, freshness status,...
get_macro_details
Fetch detailed metadata for a dbt macro. - Supply at least one of `unique_id` or `name`. Call will fail if both are ...
get_seed_details
Fetch detailed metadata for a dbt seed. - Supply at least one of `unique_id` or `name`. Call will fail if both are m...
get_semantic_model_details
Fetch detailed metadata for a dbt MetricFlow semantic model. - Supply at least one of `unique_id` or `name`. Call wi...
get_snapshot_details
Fetch detailed metadata for a dbt snapshot. - Supply at least one of `unique_id` or `name`. Call will fail if both a...
get_test_details
Fetch detailed metadata for a dbt test. - Supply at least one of `unique_id` or `name`. Call will fail if both are m...
get_related_models
Search the current environment for dbt models that are semantically similar to the given query. The search will consi...
list_metrics
List all metrics from the dbt Semantic Layer. If the user is asking a data-related or business-related question, thi...
list_saved_queries
List all saved queries from the dbt Semantic Layer. Saved queries are pre-defined queries that have been saved in th...
get_dimensions
Get the dimensions for specified metrics Dimensions are the attributes, features, or characteristics that describe o...
get_entities
Get the entities for specified metrics Entities are real-world concepts in a business such as customers, transaction...
Showing 20 of 24 tools
Works with every major client
Why Mintive gateway
Centralized governance
One-click deployment
OAuth + SSO enforcement
Host stdio servers on Mint instead of running locally
Observability and control
Enterprise hardening
Supports shared and per-user auth
Granular tool access control
FAQs
Yes. Mintive Gateway is SOC 2 compliant and uses OAuth-based authentication for all dbt Cloud MCP interactions.
ChatGPT, Claude, Claude Code, and any MCP-compatible client.
Schedule a demo to receive Mintive Gateway credentials and configuration details for connecting your AI client to the dbt Cloud MCP Server.
The Model Context Protocol (MCP) is an open standard that lets AI models connect to external tools and data sources through a single, secure interface—the "USB-C for AI."
Access is managed centrally in Mintive Gateway. Administrators can grant, suspend, or revoke connections and control authentication through identity-based policies.
Mint provides usage dashboards and audit logs for monitoring authentication, tool invocations, and connection activity.
No. Mint supports OAuth authentication and delegated token marshalling, allowing secure, automatic credential handling without manual entry.
Yes. Integrate Mint with Okta or another identity provider to enable role-based access. Map teams or groups to Virtual MCPs (VMCPs) for structured permissions.
Yes. Teams can define VMCPs with custom tool prompts, configurations, and behavior tailored to their workflows.
Yes. You can bring your own MCP servers and manage them through Mint with governance and security controls.
Create a Mintive app in Okta, upload the metadata XML, map groups to roles, and verify the connection.
Mint detects and notifies administrators of changes to tool definitions and descriptions, including new tools, renamed tools, removals, and updates to metadata.
Yes. Each invocation is logged with timestamp, user identity, and client metadata for traceable auditing.