This server provides agentic access to Oracle EPM Cloud Financial Consolidation and Close (FCCS) with dual MCP server and web API modes, featuring 40+ tools for comprehensive FCCS operations.
Comprehensive FCCS Operations: Full coverage of Oracle FCCS REST API including application management, job execution, dimension exploration, journal handling, data operations, report generation, and consolidation processes
Dual Access Modes: Functions as both an MCP server for Claude Desktop integration and a FastAPI web server for direct API access
Application & Job Management: Retrieve application details, API version information, list recent jobs, check job statuses, and run business or data load rules
Dimension & Metadata Operations: Get dimension lists and members, build parent-child hierarchies, and query local metadata cache with SQL-like filtering
Journal Management: Retrieve, filter, approve, reject, post journals, update periods, and perform bulk import/export operations
Intelligent Data Retrieval: Smart data tools with automatic 14-dimension handling, consolidation breakdown (Entity Input, Total, Proportion, Elimination, Contribution), movement dimension customization, and data copy/clear operations
Reporting Capabilities: Generate FCCS reports (Task Manager, Supplemental Data, Enterprise Journal, Consolidation Process) in multiple formats (HTML, PDF, XLSX, CSV) with async support, plus custom Python script templates for reporting
Advanced Consolidation: Export/import consolidation rulesets, validate metadata, generate intercompany matching reports, import supplementation data, and deploy form templates
Feedback & Learning System: PostgreSQL persistence with reinforcement learning tracking, user feedback submission (1-5 stars), execution history viewing, and performance metrics
Business Document Generation: Create system pitch documents and investment memos with financial analysis
Development Flexibility: Mock mode for development without real FCCS connection, bilingual English/Portuguese support, and automated setup scripts
Deployment Options: Windows, Linux/Mac, Docker, and Google Cloud Run deployment with detailed guides for each platform
Enables deployment of the FCCS agent server on Google Cloud Run platform
Stores tool execution history, feedback, and metrics for reinforcement learning tracking of FCCS operations
FCCS MCP Agentic Server
Oracle EPM Cloud Financial Consolidation and Close (FCCS) agentic server using Google ADK with MCP support.
Features
25+ FCCS Tools: Full coverage of Oracle FCCS REST API
Dual Mode: MCP server (Claude Desktop) + Web API (FastAPI)
Memory & Feedback: PostgreSQL persistence with RL tracking
Mock Mode: Development without real FCCS connection
Bilingual: English and Portuguese support
Quick Start
Windows (Recommended)
Automated Setup:
This will:
Create virtual environment
Install all dependencies
Create
.envfile from templateGuide you through configuration
Manual Setup:
Create virtual environment:
python -m venv venvActivate:
.\venv\Scripts\Activate.ps1Install:
pip install -e .Configure: Copy
.env.exampleto.envand editInitialize database:
python scripts\init_db.py(if using PostgreSQL)
Quick Commands:
Start web server:
.\start-server.batStart MCP server:
.\start-mcp-server.batInstall dependencies:
.\install-dependencies.batInitialize database:
.\init-database.bat
See WINDOWS_DEPLOYMENT.md for detailed Windows setup guide.
Linux/Mac
1. Install Dependencies:
2. Configure Environment:
3. Run:
MCP Server (for Claude Desktop):
Web Server (for API access):
Interactive CLI:
Claude Desktop Configuration
Add to %APPDATA%\Claude\claude_desktop_config.json:
API Endpoints
Endpoint | Method | Description |
| GET | Health check |
| GET | List available tools |
| POST | Execute a tool |
| POST | Call specific tool |
| POST | Submit user feedback |
| GET | Get tool metrics |
Available Tools
Application
get_application_info- FCCS application detailsget_rest_api_version- API version info
Jobs
list_jobs- List recent jobsget_job_status- Job status by IDrun_business_rule- Execute business rulesrun_data_rule- Execute data load rules
Dimensions
get_dimensions- List all dimensionsget_members- Get dimension membersget_dimension_hierarchy- Build hierarchy tree
Journals
get_journals- List journalsget_journal_details- Journal detailsperform_journal_action- Approve, reject, postupdate_journal_period- Update periodexport_journals/import_journals
Data
export_data_slice- Export grid datasmart_retrieve- Smart data retrievalcopy_data/clear_data
Reports
generate_report- Generate FCCS reportsget_report_job_status- Async report status
Consolidation
export_consolidation_rulesets/import_consolidation_rulesetsvalidate_metadatagenerate_intercompany_matching_reportimport_supplementation_datadeploy_form_template
Architecture
Deployment
Windows
See WINDOWS_DEPLOYMENT.md for complete Windows deployment guide including:
Prerequisites installation
Automated setup scripts
Windows Service configuration
Troubleshooting
Docker
Google Cloud Run
See QUICK_DEPLOY.md for detailed Cloud Run deployment.
Feedback System
The agent tracks tool executions for reinforcement learning:
Automatic: Execution time, success/failure, errors
User Feedback: 1-5 rating via
/feedbackendpointMetrics: Aggregated stats via
/metricsendpoint
Documentation
Windows Deployment Guide - Complete Windows setup
GitHub Setup Guide - Repository setup and configuration
Quick Deploy - Google Cloud Run deployment
ChatGPT Quick Start - ChatGPT integration
Dashboard Quick Start - Performance dashboard
License
MIT
fccs-mcp-ag-server
This server cannot be installed