Language: 日本語English

oracle-ai-data-platform-workbench-spark-connectors Plugin

Author
Oracle
Category
Development
Topics
Data Engineering & Analytics · Databases & Storage · Claude Code Customization & Workflow
First seen
2026-07-09
Last confirmed
2026-07-13
Explanation last updated
2026-07-12

The explanation below is AI-generated. Please verify it against the sources.

This item is a Claude Code plugin that packages skills for connecting Oracle AI Data Platform (AIDP) Workbench Spark notebooks to a wide range of data sources. According to the README, it ships 27 skills in total: 25 connector skills plus one bootstrap skill and one routing (overview) skill, covering Oracle/OCI sources (Autonomous DB family, ExaCS, generic Oracle DB, PeopleSoft, Siebel, Fusion REST/BICC, EPM Cloud, Essbase, OCI Streaming, Object Storage, Iceberg), external RDBMS/Hadoop systems (PostgreSQL, MySQL/HeatWave, SQL Server, Azure SQL, Hive), SaaS systems (Salesforce, NetSuite), and multi-cloud/escape-hatch options (Snowflake, Azure ADLS Gen2, AWS S3, generic REST, custom JDBC, Excel). Each skill generates plain Python code (Spark JDBC, structured streaming, Spark oci:///s3a:///abfss://, or REST-to-DataFrame) that runs directly in a Workbench notebook without extra runtime setup. The plugin's own description states it has been live-validated on the workbench tpcds cluster (Spark 3.5.0) with 17 PASS and 4 'ship-as-is' results out of 21 test rows, while the README notes the current version is v0.6.0, which added Azure SQL and NetSuite guidance and refreshed Snowflake support. The README also lists auth methods (e.g., Instance Principal, Resource Principal) that Workbench notebooks do not currently support, routing users to API Key + inline PEM instead.

Overview

Oracle AI Data Platform Workbench is Oracle's cloud service, described on its homepage as simplifying cataloging, ingesting, and analyzing data, and providing the platform/framework for building data analytics pipelines, notebooks, workflows, and AI agents. This plugin is a Claude Code extension (not the platform itself) that adds model-invokable skills so that, within a Claude Code session against an AIDP Workbench workspace, Claude can generate ready-to-run Spark connector code for the data source a user describes.

What you can do with oracle-ai-data-platform-workbench-spark-connectors

  • Ask Claude to connect a Workbench Spark notebook to Oracle sources such as Autonomous DB (ALH/ADW/ATP), ExaCS, generic Oracle DB, PeopleSoft, or Siebel
  • Pull data from Fusion ERP/HCM/SCM (REST or BICC bulk extracts), EPM Cloud Planning, or Essbase 21c into a Spark DataFrame
  • Read/write OCI Streaming (Kafka), OCI Object Storage, or Apache Iceberg tables from a notebook
  • Connect to external RDBMS systems: PostgreSQL, MySQL/HeatWave, SQL Server, Azure SQL, or Hive
  • Connect to SaaS systems Salesforce and NetSuite (both read-only per the README)
  • Use multi-cloud or escape-hatch connectors: Snowflake (read-only), Azure ADLS Gen2, AWS S3, a generic REST connector, custom JDBC drivers, or Excel (.xlsx) files
  • Run a one-time bootstrap skill to install the helper package into the workspace before using other connectors
  • Review per-connector example notebooks and live-test result tables included in the repository

Sources

Original description (English)

Oracle AI Data Platform Workbench Spark connectors for Claude Code. 18 connector skills covering every data source workbench customers commonly need: Oracle Autonomous DB family (ALH/ADW/ATP) via wallet/IAM-DB-Token/API-key, ExaCS, Fusion ERP REST, Fusion BICC, EPM Cloud Planning, Essbase 21c, OCI Streaming (Kafka), OCI Object Storage, Apache Iceberg, plus external systems (PostgreSQL, MySQL/HeatWave, SQL Server, Snowflake, Azure ADLS Gen2, AWS S3, generic REST, custom JDBC, Excel). Live-validated on the workbench `tpcds` cluster (Spark 3.5.0): 17 PASS / 4 ship-as-is out of 21 test rows.

History of oracle-ai-data-platform-workbench-spark-connectors

Back to list