Connect AI agents to Oracle EPM Cloud (Planning, PBCS, EPBCS) via REST APIs. Automate month-end close, run business rules, manage substitution variables, refresh databases, export data slices, and monitor job status through natural language. Supports mock mode for testing without an EPM environment. Built by Fred Mamadjanov, Oracle ACE and EPM Solution Architect.
Overview
Oracle EPM Cloud MCP Server
Connect Claude AI (or any MCP-compatible client) to Oracle EPM Cloud via REST APIs.
What You Can Do
Ask your AI agent to perform Oracle EPM operations in natural language:
- "What applications are in my EPM environment?"
- "Show me the current substitution variables"
- "Run the Agg_AllData business rule"
- "Export Q1 revenue data for North America"
- "Roll the current month forward from Mar to Apr"
Available Tools
- get_api_version — Test connectivity and discover API versions
- list_applications — List all EPM applications
- get_substitution_variables — Read current month, year, scenario variables
- run_business_rule — Execute a calc script or business rule
- check_job_status — Poll whether a job completed or errored
- export_data_slice — Pull data from the cube by dimension members
- update_substitution_variable — Change a substitution variable value
Use Case: Month-End Close Automation
The server enables AI-driven automation of the monthly close cycle — check the current period, run aggregation rules, validate data, roll the period forward, and confirm. The same workflow finance teams do manually each month, now executable through conversation.
Mock Mode
Runs out of the box without an Oracle EPM environment. Mock mode returns realistic sample data so you can test the full workflow before connecting to a live system.
Built By
Fred Mamadjanov — Oracle ACE, EPM Solution Architect | fmepm.com
Server Config
{
"mcpServers": {
"oracle-epm-cloud": {
"command": "node",
"args": [
"/path/to/oracle-epm-mcp-server/index.js"
]
}
}
}