Data Lineage Source

The Data Lineage integration allows the MCP Toolbox to connect to the Google Cloud Data Lineage API.

About

The Data Lineage integration allows the MCP Toolbox to connect to the Google Cloud Data Lineage API. It enables large language models to query and analyze data lineage, representing the flow of data between source (upstream) and target (downstream) assets.

This integration supports:

  • Entity-Level Lineage: Tracking data flow between entire assets (e.g., tables, files).
  • Column-Level Lineage (CLL): Tracking data flow between specific fields or columns within assets.

Available Tools

Data Lineage Source Tools

Tool NameDescription
datalineage-search-lineageA "datalineage-search-lineage" tool allows to retrieve a streaming response of lineage links connected to the requested assets.

Example

Here is an example configuration for the Data Lineage source:

kind: source
name: my-lineage-source
type: datalineage
project: my-gcp-project-id

Reference

fieldtyperequireddescription
namestringtrueUnique name for this source instance.
typestringtrueMust be “datalineage”.
projectstringtrueThe Google Cloud Project ID where the lineage events are stored.