MCP server for dbt-core (OSS) users as the official dbt MCP only supports dbt Cloud. Supports project metadata, model and column-level lineage and
If you want an AI assistant working directly with Dbt, the dbt mcp server is the bridge. MCP server for dbt-core (OSS) users as the official dbt MCP only supports dbt Cloud. Supports project metadata, model and column-level lineage and dbt documentation.
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.
Once connected, the assistant can call this tool directly:
Column — Level Lineage:**Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
The server reads 3 environment variables: MANIFEST_PATH, SCHEMA_MAPPING_PATH, MANIFEST_CL_PATH. Keep credentials in your client's env block or a secrets manager rather than committing them.
Knowledge and memory servers address the most frustrating trait of language models — walking into every conversation with no recollection of the last one. Dbt sits in that group, and the shape of its toolset — Column — tells you what it is really for. Worth comparing against the other knowledge memory servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Column | Level Lineage:** |
| Variable | Description | Required |
|---|---|---|
| MANIFEST_PATH | Filesystem location the server is allowed to use. | Optional |
| SCHEMA_MAPPING_PATH | Filesystem location the server is allowed to use. | Optional |
| MANIFEST_CL_PATH | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.