AI-Powered · Free · Open Ecosystem

Talk to Your Oracle Fusion

powered by ofrag — Oracle Fusion RAG Engine

Let AI agents query your ERP data with natural language

Semantic search across 25,000+ tables · AST-based SQL validation · MCP Server for Claude, Gemini & other LLMs · 4-second query execution

How It Works

ofrag is an MCP Server that gives AI agents structured, safe access to your Oracle Fusion data

Ask in Plain Language

Your AI agent receives a question like "Show me unpaid invoices from Acme Corp last month"

Semantic Discovery

ofrag finds the right tables and REST APIs using vector embeddings and business process mapping — no hardcoded queries needed

Validate Locally

SQL is parsed into an AST and validated against a cached schema. Only clean, verified queries reach your database

Execute & Return

The validated query runs against Oracle Fusion and results come back in about 4 seconds, formatted and ready to use

Live Example
"Show me the top 5 unpaid invoices for vendor Acme Corp generated last month"
ofrag interprets "unpaid" as PAYMENT_STATUS_FLAG = 'N', discovers the correct AP tables via semantic search, validates the SQL against the local schema cache, executes it on Oracle Fusion, and returns a formatted table — all without the user knowing a single table name.
~4 seconds end-to-end

ofrag — AI Intelligence Layer for Oracle Fusion

Everything your AI agent needs to understand and interact with Oracle Fusion Cloud

Semantic Search

Find relevant tables and APIs using natural language. Vector embeddings across 25,000+ table descriptions and 500+ REST resources. Understands business intent — "money from customers" finds AR tables even without exact matches.

AST-Based SQL Validation

Every query is parsed into an Abstract Syntax Tree and validated against a locally cached schema before execution. The AI gets precise feedback like "column VENDOR_NAME does not exist in AP_INVOICES_ALL" — preventing hallucinations.

MCP Server Protocol

Native integration with Claude, Gemini, and any MCP-compatible LLM. Tools include semantic_search, execute_oracle_sql, rest_call, lint_sql, module_summary, and more — giving AI structured access to your ERP.

Universal REST Client

Full CRUD operations on Oracle Fusion REST APIs. Self-discovering endpoints — the AI calls /describe to understand resource structure dynamically. Automatic pagination for bulk exports.

Local Intelligence

All metadata exploration happens locally — zero queries to production during discovery. Schema cache, fuzzy search, synonym expansion, and business process cross-referencing run at zero latency.

Multi-Environment

Switch between dev, SIT, UAT, and production instantly. Mixed authentication per environment (SSO or basic auth). Compare data across environments without configuration changes.

OFJDBC — The SQL Foundation

Free, open-source JDBC driver that powers direct SQL access to Oracle Fusion Cloud. The engine behind the ecosystem.

Direct SQL Query Access

Execute SQL queries directly against Oracle Fusion Cloud without creating OTBI reports. Get instant results for troubleshooting, analysis, and data exploration with DBeaver's intelligent autocomplete.

Multi-Cloud Data Integration

Build complete ETL pipelines from Oracle Fusion to AWS (S3, Athena, QuickSight), Google Cloud (BigQuery, Cloud Storage), Azure (Synapse, Blob Storage, Power BI), or OCI (Object Storage, Data Lake).

Works with DBeaver

Seamlessly integrates with DBeaver, the premier free database IDE. Local metadata caching for instant autocomplete, real-time error detection, and intelligent table/column suggestions.

Export to Any Format

Export query results to Parquet (partitioned), CSV, JSON, Excel, or load directly into DuckDB, PostgreSQL, MySQL, or cloud databases. Build data lakes without custom scripts.

JVM & Airflow Support

Standard JDBC driver — works in Java, Kotlin, Scala, Groovy, Apache Airflow (JdbcOperator), Talend, Pentaho, and Apache NiFi. For non-JVM languages, use OFArrow with Arrow Flight SQL.

BI & Analytics Platforms

Connect QuickSight, Power BI, Tableau, or Looker to Oracle Fusion data via cloud data warehouses populated by OFJDBC pipelines.

Frequently Asked Questions

What is the Oracle Fusion RAG Engine (ofrag)?

ofrag is a Retrieval-Augmented Generation engine and MCP Server that enables AI agents like Claude and Gemini to intelligently query Oracle Fusion Cloud. It provides semantic search across 25,000+ table descriptions, AST-based SQL validation, and live query execution — letting your AI understand and retrieve ERP data using natural language.

How does semantic search work for Oracle Fusion?

ofrag's semantic search operates in two modes. The lightweight mode uses keyword matching, synonym expansion, and business process cross-referencing with zero external dependencies. The enhanced mode adds vector embeddings (Gemini Embedding 2) across 25,000+ table descriptions and 500+ REST API resources, understanding queries like "money received from customers" even when exact terms don't match any table name.

Can I use AI to query Oracle Fusion Cloud data?

Yes. ofrag is an MCP Server that connects AI agents directly to Oracle Fusion Cloud. The AI agent can search for relevant tables using natural language, validate SQL queries against cached schemas, and execute them in real-time — typically returning results in about 4 seconds.

What is MCP and how does ofrag use it?

MCP (Model Context Protocol) is an open standard that lets AI agents use external tools. ofrag implements MCP to provide Claude, Gemini, and other LLMs with tools like semantic_search, execute_oracle_sql, rest_call, lint_sql, and more — giving the AI structured access to Oracle Fusion data while keeping production databases protected.

How does ofrag protect production databases?

ofrag uses local intelligence — it caches Oracle Fusion metadata locally and performs all exploration (schema search, SQL validation, semantic parsing) without touching the production database. Only final, validated queries reach the live system, preventing exploratory load on production.

Can ofrag work with multiple Oracle Fusion environments?

Yes. Switch between dev, SIT, UAT, and production environments instantly without config changes. Each environment can use different authentication methods (SSO or basic auth), and you can compare data across environments.

How do I run SQL queries against Oracle Fusion without OTBI?

OFJDBC is a free, open-source JDBC driver that lets you run SQL queries directly using DBeaver or any JDBC-compatible tool. No OTBI reports needed. For AI-powered access, use ofrag — it lets AI agents write, validate, and execute SQL queries through natural language.

How to connect DBeaver to Oracle Fusion Cloud?

Download the OFJDBC JAR from GitHub releases, add it to DBeaver as a custom JDBC driver, and connect using your Oracle Fusion Cloud URL and credentials. DBeaver will automatically cache Oracle Fusion metadata for autocomplete.

Is there a free alternative to commercial Oracle Fusion SQL tools?

Yes. OFJDBC is a 100% free, open-source JDBC driver that provides the same direct SQL query access as commercial tools like SQLConnect or DataFusing. Combined with ofrag, you also get AI-powered querying — something no commercial tool offers.

Can I use OFJDBC with Apache Airflow?

Yes. Apache Airflow has built-in JDBC support through JdbcOperator and JdbcHook. Use OFJDBC to build ETL pipelines that extract data from Oracle Fusion on a schedule. For Python-native code, use OFArrow with Arrow Flight SQL.

Is the platform secure?

Yes. Both ofrag and OFJDBC connect directly from your machine to Oracle Fusion Cloud. No data passes through third-party servers. ofrag processes all metadata exploration locally, and only validated queries reach production. OFJDBC source code is fully available on GitHub.