Knowledge Catalog MCP Server

The Knowledge Catalog (formerly known as Dataplex) Model Context Protocol (MCP) Server gives AI-powered development tools the ability to work with your Google Cloud Knowledge Catalog. It supports searching and looking up entries and aspect types.

Features

An editor configured to use the Knowledge Catalog MCP server can use its AI capabilities to help you:

Search Catalog - Search for entries in Knowledge Catalog
Explore Metadata - Lookup specific entries and search aspect types

Prerequisites

Node.js installed.
A Google Cloud project with the Dataplex API enabled.
Ensure Application Default Credentials are available in your environment.
IAM Permissions:
- Dataplex Viewer (roles/dataplex.viewer) or equivalent permissions to read catalog entries.

Install & Configuration

In the Antigravity MCP Store, click the "Install" button.

[!NOTE] On first use, the installation process automatically downloads and uses MCP Toolbox >=0.26.0. To update MCP Toolbox, use: npm i -g @toolbox-sdk/server@latest To always run the latest version, update the MCP server configuration to use: npx -y @toolbox-sdk/server@latest --prebuilt dataplex.
Add the required inputs in the configuration pop-up, then click "Save". You can update this configuration at any time in the "Configure" tab.

You'll now be able to see all enabled tools in the "Tools" tab.

[!NOTE] If you encounter issues with Windows Defender blocking the execution, you may need to configure an allowlist. See Configure exclusions for Microsoft Defender Antivirus for more details.

Usage

Once configured, the MCP server will automatically provide Knowledge Catalog capabilities to your AI assistant. You can:

"Search for entries related to 'sales' in Knowledge Catalog."
"Look up details for the entry 'projects/my-project/locations/us-central1/entryGroups/my-group/entries/my-entry'."

Server Capabilities

The Knowledge Catalog MCP server provides the following tools:

Tool Name	Description
`search_entries`	Search for entries in Knowledge Catalog.
`lookup_entry`	Retrieve specific subset of metadata (for example, schema, usage, business overview, and contacts) of a specific data asset.
`search_aspect_types`	Find aspect types relevant to the query.
`lookup_context`	Retrieve rich metadata regarding one or more data assets along with their relationships.

Custom MCP Server Configuration

The MCP server is configured using environment variables.

bash

export DATAPLEX_PROJECT="<your-gcp-project-id>"

Add the following configuration to your MCP client (e.g., settings.json for Gemini CLI, mcp_config.json for Antigravity):

json

{
  "mcpServers": {
    "dataplex": {
      "command": "npx",
      "args": ["-y", "@toolbox-sdk/server", "--prebuilt", "dataplex", "--stdio"],
      "env": {
        "DATAPLEX_PROJECT": "your-project-id"
      }
    }
  }
}

Documentation

For more information, visit the Knowledge Catalog documentation.