"dbt" matching MCP servers:

A MCP (Model Context Protocol) server for interacting with dbt.

Enables agents to inspect dbt model semantics, retrieve contracts and lineage, and verify that edits do not change what models mean.

MCP server that provides tools to interact with dbt, including dbt Core, Cloud CLI, Semantic Layer, and Discovery API.

Enables AI agents to inspect, query, test, and safely fix dbt projects and BigQuery warehouses under policy-enforced controls, with read-only direct queries and dbt-only allowlisted writes.

Enables AI clients to automatically investigate dbt test failures, trace root cause through BigQuery lineage, and generate plain-English incident reports.

Enables interaction with dbt projects via the Model Context Protocol for data analysis and insights.

MCP (model context protocol) server for interacting with dbt Docs

A minimal, extensible MCP server to run dbt models via CLI, HTTP API, or AI interfaces like Claude, with Slack notifications for task completions.

Enables AI assistants to interact with DBT (Data Build Tool) projects, allowing them to query project metadata, inspect models and sources, view compiled SQL, and run DBT commands.

A read-only MCP server that exposes dbt project artifacts and data quality result tables (BigQuery/Postgres) to LLM clients, enabling deep introspection, run-history analysis, source freshness, test coverage, and lineage walks.

A Model Context Protocol server for managing and executing dbt Cloud jobs via Claude, with search, run history, and job triggering capabilities, including safety confirmations.

Enables the analysis of DBT manifests with automatic schema version detection and lineage tracking, allowing users to query model dependencies, access compiled code, and get detailed model information.

A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.

Enables LLM agents to query governed GA4 metrics over MCP, returning definitions, assumptions, and failure modes from a MetricFlow semantic layer without writing SQL.

Exposes a governed semantic layer to AI agents so they select metrics and dimensions from a closed, engineer-declared vocabulary instead of writing SQL. Validates every typed call against the contract, rejects out-of-contract requests with structured errors and suggestions, and returns query rows together with the compiled SQL and dbt lineage for auditing.

Enables an AI assistant to query and browse multiple database engines read-only, with the ability to switch connections and engines dynamically during a session.

Read-only-by-default MCP server for Datanika, an open-source dlt + dbt-core data pipeline platform: browse connections, introspect and preview source tables, compile and run dbt transformations, and monitor pipeline runs. 25 tools (17 read-only, plus 8 write tools gated behind --allow-write); source lives in the datanika-mcp/ subdirectory of the repo.

A typed stdio/HTTP MCP server that lets agents drive governed portfolio-company data onboarding: profiling sources, inferring entities and joins, proposing canonical mappings, generating and sandbox-testing dbt artifacts, and publishing only human-certified results. It exposes agent and reviewer-only tools, tenant-scoped run/ontology/evidence resources, and guided prompts, keeping every calculation deterministic and every approval with a human.

Enables agents to interact with MySQL databases securely, supporting multi-database read-only queries, protected DML writes, and streaming exports to Sandbox Datasets.

Enables large language models to retrieve up-to-date and correct information about dlt pipelines, datasets, and schemas, improving AI-assisted development.