Oracle Fusion HCM MCP

Oracle Fusion HCM MCP

Enables interaction with Oracle Fusion HCM via REST, SOAP, SQL, and BPM, supporting catalog search, operation execution, ESS processes, BI Publisher reports, security diagnostics, and workflow management.

Category
Visit Server

README

Oracle Fusion HCM MCP

Local Oracle Fusion HCM MCP server backed by normalized Oracle REST API catalogs.

The current server intentionally has no caller authentication. It binds to 127.0.0.1 by default for local and demo-pod development. Oracle credentials, when configured, are used only by the outbound Oracle connector.

Included

  • Organization, environment and Oracle HCM reference-data schemas
  • REST, SOAP, named-SQL and HAR capability catalog
  • Default-deny authorization policy model
  • Read-only named query templates
  • Standard MCP tool result and error envelopes
  • Fusion AI Agent Studio-ready per-tool outputSchema, structuredContent, compact JSON fallback, presentation hints, and server usage instructions
  • Single-copy MCP embedded resources for binary catalog, Publisher, and report artifacts
  • Privacy-conscious audit events
  • Sanitized API artifact registry
  • Official Oracle OpenAPI importer and normalized operation catalog
  • MCP Streamable HTTP server with hcm_catalog_search
  • Full operation and schema inspection with hcm_describe_operation
  • Multi-organization environment registry with secret references
  • Connection and Basic Auth diagnostics for each Oracle pod
  • Explicit capability report for REST, SQL, security and BPM by environment
  • Contract-validated execution of official Oracle REST GET, POST, PUT, PATCH and DELETE operations, controlled by each environment's writeMode
  • Searchable ESS process catalog plus request submission, recurring schedules, status polling, bounded waiting, listing and cancellation
  • Reviewed named SQL and guarded ad-hoc SQL through BI Publisher Get SQL
  • Allowlisted BI Publisher report execution
  • Reusable OTBI .catalog dependency check, recursive export, local import preview, confirmed asynchronous import, and job verification
  • Typed WebCatalogService item inspection/listing and BI Publisher CatalogService folder listing, object metadata, existence, individual download/upload, and folder creation tools
  • HCM security diagnostics for SCIM users, roles, data roles, profiles, role mappings, Areas of Responsibility and security-policy reports
  • BPM approval-rule inventory, rule/task inspection, usage search, snapshots and cross-environment comparison
  • BPM runtime Worklist, task history, HCM transaction context, Transaction Console search and combined task diagnosis
  • Approval Rules simulation reports and simulation history
  • Optimistic-lock and confirmation protected BPM draft/deploy support, disabled by default
  • Allowlisted BPM runtime task actions with optimistic state/date checks and an identical code path for every target environment
  • Batch Transaction Console approve, reject, reassign, resubmit and withdraw actions with fresh-status checks, preview, exact confirmation and post-action verification
  • Reusable Oracle REST client with Basic Auth, pagination and retry handling
  • Read-only end-to-end smoke command using the official MCP client
  • Valid configuration examples and security invariant tests

Commands

npm install
npm run check
npm run start:local
npm run hcm:smoke -- <environmentId>
npm run import:openapi

See the data model for the entity relationships and security invariants. See the OpenAPI importer for source and generated-catalog details. See the local MCP server guide for tools and the current authentication boundary. See environment configuration for multi-pod setup and connection tests. See Catalog/Support tools for SQL, security and BPM configuration. See the BI catalog bundle guide for packaging Get SQL and Security reports once and deploying them to other pods. See Oracle BI catalog tools for the WebCatalogService and Publisher CatalogService boundary. See the Fusion AI Agent Studio integration guide for MCP registration, the common result contract, workflow rendering, and debugging. The v0.10 test report records the SDK, schema, sanitization, and binary-delivery validation; the v0.8 test report remains the latest demo-pod connector validation.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured