Prepare the server locally
Run this once before adding it to Claude Code.
npm run install-deps
npm run build
gemini extensions install .Register it in Claude Code
claude mcp add -e "DATALOG_API_KEY=${DATALOG_API_KEY}" datalog-studio -- node /path/to/datalog-studio/index.jsReplace any placeholder paths in the command with the real path on your machine.
DATALOG_API_KEY+ 2 optionalMake your agent remember this setup
datalog-studio's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Catalog discovery for workspace data exploration
- Master data management for collections and attributes
- Data asset control for listing and analyzing uploaded files
- Direct data ingestion with automated AI transformation
Tools 5
list_catalogsList all accessible data catalogs.list_collectionsList collections in a specific catalog.list_attributesView collection schema and attributes.list_data_assetsList uploaded files within a collection.ingest_dataIngest master data into a collection.Environment Variables
DATALOG_API_KEYrequiredAPI key for authenticating with Datalog Studio.DATALOG_APICustom domain endpoint for enterprise installations.CATALOG_URIAPI path suffix for custom enterprise installations.Try it
Original README from igot-ai/datalog-studio
Catalog MCP Extension
Professional MCP server for integrating Catalog tasks into the Gemini CLI. Manage data catalogs, collections, and master data using natural language.
Features
- Catalog Discovery: List and find data catalogs within your workspace.
- Master Data Management: Explore collections, attributes, and AI prompt templates.
- Data Asset Control: List uploaded documents and analyze data structures.
- Data Ingestion: Direct data ingestion with automated AI transformation.
Quick Start
1. Prerequisites
- Node.js (v18+) and npm installed.
2. Installation
Install the extension and its dependencies:
npm run install-deps
npm run build
gemini extensions install .
3. Configuration
The extension requires a DATALOG_API_KEY. By default, it connects to https://studio.igot.ai/v1/catalog.
For custom enterprise installations, you can configure the endpoint using:
DATALOG_API: The domain endpoint (e.g.,https://enterprise.com).CATALOG_URI: The API path suffix (e.g.,/v1/catalog).
Development
Use the provided scripts for a professional development workflow:
npm run dev: Start MCP server in watch mode.npm run lint: Run ESLint to find and fix issues.npm run format: Format code with Prettier.npm run typecheck: Run TypeScript type checking.npm run preflight: Run a full cleanup, install, lint, and build cycle.
Tools Summary
list_catalogs(): List all accessible data catalogs.list_collections(catalog_id): List collections in a specific catalog.list_attributes(catalog_name, collection_name): View collection schema and attributes.list_data_assets(catalog_name, collection_name): List uploaded files within a collection.ingest_data(catalog_name, collection_name, text, transform?): Ingest master data into a collection.