dbt-docs-mcp

MCP server for querying dbt project metadata and lineage

Stars

Forks

Watchers

Issues

dbt-docs-mcp implements a Model Context Protocol (MCP) server that interacts with dbt project metadata artifacts such as manifest.json and catalog.json. It exposes the dbt project graph through a standardized API, enabling search and inspection of models, sources, columns, and their upstream/downstream lineage. The solution facilitates column-level and model-level lineage analysis, node inspection, and can be extended to support database metadata querying and custom knowledge bases. It is designed for integrations with MCP-compatible clients, supporting advanced data discovery and context sharing workflows.

Key Features

Serves as an MCP-compliant API for dbt project metadata

Search dbt nodes by name, type, or column

Search within compiled SQL code of dbt nodes

Retrieve detailed attributes for any node by unique ID

Explore model and column-level lineage (upstream/downstream)

Generates column-level lineage from dbt artifacts

Supports custom extensions such as SQL execution and direct database metadata retrieval

Integrates with MCP-compatible clients like Claude desktop and Cursor

Offers tools to parse and process dbt manifest and catalog files

Facilitates advanced search for knowledge base entries

Use Cases

Querying and visualizing dbt model and column lineage in analytics platforms

Automating data discovery and documentation tasks for data teams

Debugging and impact analysis for changes in dbt projects

Supporting AI/data agents needing access to detailed dbt graph metadata

Enhancing data catalog or governance tools with column-level lineage

Integrating dbt metadata into knowledge base search systems

Automating quality control and code review workflows for data models

Building custom dashboards or UIs for dbt lineage exploration

Enabling fine-grained dependency tracing for compliance and audit purposes

Facilitating collaborative workflows between data engineers and analysts using MCP clients

README

dbt-docs-mcp

Model Context Protocol (MCP) server for interacting with dbt project metadata, including dbt Docs artifacts (manifest.json, catalog.json). This server exposes dbt graph information and allows querying node details, model/column lineage, and related metadata.

Key Functionality

This server provides tools to:

Search dbt Nodes:
- Find nodes (models, sources, tests, etc.) by name (search_dbt_node_names).
- Locate nodes based on column names (search_dbt_column_names).
- Search within the compiled SQL code of nodes (search_dbt_sql_code).
Inspect Nodes:
- Retrieve detailed attributes for any given node unique ID (get_dbt_node_attributes).
Explore Lineage:
- Find direct upstream dependencies (predecessors) of a node (get_dbt_predecessors).
- Find direct downstream dependents (successors) of a node (get_dbt_successors).
Column-Level Lineage:
- Trace all upstream sources for a specific column in a model (get_column_ancestors).
- Trace all downstream dependents of a specific column in a model (get_column_descendants).
Suggested extensions:
- Tool that allows executing SQL queries.
- Tool that retrieves table/view/column metadata directly from the database.
- Tool to search knowledge-base.

Getting Started

Prerequisites: Ensure you have Python installed and uv

Clone the repo:

bash

git clone <repository-url>
cd dbt-docs-mcp

Optional: parse dbt manifest for column-level lineage:
- Setup the required Python environment, e.g.:
bash
```
uv sync
```
- Use the provided script scripts/create_manifest_cl.py and simply provide the path to your dbt manifest, dbt catalog and the desired output paths for your schema and column lineage file:
bash
```
python scripts/create_manifest_cl.py --manifest-path PATH_TO_YOUR_MANIFEST_FILE --catalog-path PATH_TO_YOUR_CATALOG_FILE --schema-mapping-path DESIRED_OUTPUT_PATH_FOR_SCHEMA_MAPPING --manifest-cl-path DESIRED_OUTPUT_PATH_FOR_MANIFEST_CL
```
- Depending on your dbt project size, creating column-lineage can take a while (hours)

Run the Server:

If your desired MCP client (Claude desktop, Cursor, etc.) supports mcp.json it would look as below:

json

{
    "mcpServers": {
        "DBT Docs MCP": {
        "command": "uv",
        "args": [
            "run",
            "--with",
            "networkx,mcp[cli],rapidfuzz,dbt-core,python-decouple,sqlglot,tqdm",
            "mcp",
            "run",
            "/Users/mattijs/repos/dbt-docs-mcp/src/mcp_server.py"
        ],
        "env": {
            "MANIFEST_PATH": "/Users/mattijs/repos/dbt-docs-mcp/inputs/manifest.json",
            "SCHEMA_MAPPING_PATH": "/Users/mattijs/repos/dbt-docs-mcp/outputs/schema_mapping.json",
            "MANIFEST_CL_PATH": "/Users/mattijs/repos/dbt-docs-mcp/outputs/manifest_column_lineage.json"
        }
        }
    }
}

Star History

Repository Owner

mattijsdp

User

Repository Details

Language Python

Default Branch main

Size 142 KB

Contributors 3

License MIT License

MCP Verified Nov 12, 2025

Programming Languages

Python

100%

Related MCPs

Discover similar Model Context Protocol servers

MCP-Typescribe

An MCP server for serving TypeScript API context to language models.

MCP-Typescribe is an open-source implementation of the Model Context Protocol (MCP) focused on providing LLMs with contextual, real-time access to TypeScript API documentation. It parses TypeScript (and other) definitions using TypeDoc-generated JSON and serves this information via a queryable server that supports tools used by AI coding assistants. The solution enables AI agents to dynamically explore, search, and understand unknown APIs, accelerating onboarding and supporting agentic behaviors in code generation.

⭐ 45
MCP
yWorks/mcp-typescribe

Alkemi MCP Server

Integrate Alkemi Data sources with MCP Clients for seamless, standardized data querying.

Alkemi MCP Server provides a STDIO wrapper for connecting Alkemi data sources—including Snowflake, Google BigQuery, and Databricks—with MCP Clients using the Model Context Protocol. It facilitates context sharing, database metadata management, and query generation through a standardized protocol endpoint. Shared MCP Servers allow teams to maintain consistent, high-quality data querying capabilities without needing to replicate schemas or query knowledge for each agent. Out-of-the-box integration with Claude Desktop and robust debugging tools are also included.

⭐ 2
MCP
alkemi-ai/alkemi-mcp

NyxDocs

MCP server for real-time cryptocurrency project documentation and insights.

NyxDocs is a Model Context Protocol (MCP) compatible server built in Python for managing and serving up-to-date documentation for cryptocurrency projects. It aggregates information from multiple sources such as CoinGecko, GitHub, GitBook, Notion, and official websites, providing real-time data and updates on blockchain ecosystems. Featuring tools for searching projects, retrieving detailed info, extracting documentation, and monitoring changes, it is tailored for developers and AI contexts needing access to accurate crypto documentation. The architecture leverages a FastMCP-based server core, automated document scrapers, and supports multi-blockchain environments.

⭐ 3
MCP
nyxn-ai/NyxDocs

Chainlist MCP Server

Fast, structured EVM chain info for AI agents via the Model Context Protocol

Chainlist MCP Server enables AI agents and MCP-compatible clients to quickly access and search verified EVM blockchain data. It sources data from Chainlist.org and provides efficient REST-like tools for retrieving details by chain ID or searching by keyword. The server outputs structured Markdown responses, supporting AI context integration with tabulated RPC endpoints and explorers for clarity.

⭐ 2
MCP
kukapay/chainlist-mcp

MCP Server for Data Exploration

Interactive Data Exploration and Analysis via Model Context Protocol

MCP Server for Data Exploration enables users to interactively explore and analyze complex datasets using prompt templates and tools within the Model Context Protocol ecosystem. Designed as a personal Data Scientist assistant, it facilitates the conversion of raw data into actionable insights without manual intervention. Users can load CSV datasets, run Python scripts, and generate tailored reports and visualizations through an AI-powered interface. The server integrates directly with Claude Desktop, supporting rapid setup and seamless usage for both macOS and Windows.

⭐ 503
MCP
reading-plus-ai/mcp-server-data-exploration

Databricks Genie MCP Server

Bridge natural language queries to Databricks Genie via Model Context Protocol.

Databricks Genie MCP Server enables interaction between large language models and the Databricks Genie API using the Model Context Protocol. It allows users to ask natural language questions, start and manage conversations, and run SQL queries in Genie spaces. The tool provides structured results, supports follow-up queries, and facilitates connection through both standard and Docker-based setups. Designed for use with Claude Desktop, it streamlines conversational analytics within Databricks workspaces.

⭐ 12
MCP
yashshingvi/databricks-genie-MCP

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

dbt-docs-mcp

Key Features

Use Cases

README

dbt-docs-mcp

Key Functionality

Getting Started

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Related MCPs