oracle-vo-ai-mcp

aNOOBhav/oracle-vo-ai-mcp

3.1

If you are the rightful owner of oracle-vo-ai-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

This project provides an MCP server that integrates Oracle Fusion’s BICC VO metadata extraction with Claude Desktop, allowing users to query metadata using natural language.

Oracle VO MCP

A Cline-compatible MCP server for extracting and managing Oracle Fusion BICC View Object (VO) metadata.

Features

  • Extract metadata for Oracle Fusion PVOs and VOs.
  • Summarize metadata using natural language.
  • Save metadata into Excel/CSV for further analysis.
  • Expose MCP server endpoints for integration with Cline or other AI agents.

Installation

  1. Clone this repository:

    git clone <repository-url>
cd oracle-vo-mcp

  2. Install dependencies using uv:

    uv sync

  3. Create a .env file with your Fusion credentials:

    FUSION_USERNAME=your_username
FUSION_PASSWORD=your_password
FUSION_URL=https://yourfusionhost.fa.oraclecloud.com

Usage

Run the MCP server

uv run oracle_vo_mcp.py

This will start the MCP server locally.

Register with Cline

To connect with Claude Desktop (Cline):

  1. Open your cline_mcp_settings.json file.
  2. Add the following entry:
{
  "mcpServers": {
    "oracle-vo-mcp": {
      "command": "uv",
      "args": ["run", "oracle_vo_mcp.py"],
      "env": {
        "FUSION_USERNAME": "your_username",
        "FUSION_PASSWORD": "your_password",
        "FUSION_URL": "https://yourfusionhost.fa.oraclecloud.com"
      }
    }
  }
}
  1. Restart Claude Desktop. The MCP server will now be available in Cline.

Configuration

The MCP server reads from your .env file or cline_mcp_settings.json environment variables:

  • FUSION_USERNAME → Oracle Fusion username
  • FUSION_PASSWORD → Oracle Fusion password
  • FUSION_URL → Fusion environment base URL

Development

Run tests

pytest

Code formatting

black .
isort .

Type checking

mypy .

Oracle Fusion PVOs

Pseudo View Objects (PVOs) in Oracle Fusion BICC are metadata-driven objects that expose application data in a consumable format for reporting and integration.

They are useful because:

  • They abstract complex table joins into a single extractable VO.
  • They provide consistent metadata across environments.
  • They enable data lineage tracking for Fusion reports.

When PVO metadata is not readily available:

  • It can be queried using BICC extract job details.
  • Metadata can also be retrieved from Fusion SOAP/REST services.
  • Access depends on roles and privileges granted in Fusion security.

Example: BillingPlanExtractPVO exposes billing plan details for subscription and revenue recognition.

License

MIT