IFS Developer Intelligence MCP Server
An enterprise MCP server that transforms IFS Cloud documentation, local code, and Oracle error knowledge into AI-powered development intelligence, offering 60+ tools for code generation, review, error diagnosis, and deployment.
README
IFS Engineering Copilot Enterprise vNext
An enterprise-grade, multi-agent AI engineering copilot platform transforming official IFS Cloud Technical Documentation (docs.ifs.com), IFS Academy Resource Portal (resourceportal.ifsacademyworld.com), IFS Community Forum (community.ifs.com), local workspace models (*.entity, *.projection, *.client, *.plsql), and Oracle DBA knowledge into a senior-level Engineering Copilot for IFS Cloud development.
🚀 Key Architectural Capabilities (Version Next Release)
1. Multi-Agent Request Orchestrator (src/engine/multiAgentOrchestrator.ts)
- Virtual Agent Dispatcher: Coordinates specialized Virtual Agents (Documentation Agent, Workspace Agent, PL/SQL Agent, Marble Agent, DBA Agent, Security Agent, Impact Analysis Agent, Quality Gate Agent).
- Evidence Synthesis: Combines agent findings into a single, evidence-backed response.
2. Reciprocal Rank Fusion (RRF) & Semantic Synonym Engine (src/rag/hybridSearch.ts)
- RRF RAG Pipeline: Upgraded search scoring using Reciprocal Rank Fusion ($k=60$).
- IFS Domain Synonyms: Automatic domain expansion (e.g. searching "VAT" expands to search
TAX_CALCULATION_APIandSTATUTORY_FEE_API).
3. Real-Time Telemetry & Observability Subsystem (src/engine/telemetryEngine.ts)
- Track request volumes, tool execution counts, latency in milliseconds, tool success/failure rates, and confidence score distribution.
- Live public endpoints:
https://ifs-mcp-server.onrender.com/metrics&https://ifs-mcp-server.onrender.com/health.
4. Consensus & Evidence Comparison Engine (src/engine/consensusEngine.ts)
- Cross-references evidence across Official TechDocs, IFS Academy, IFS Community, Oracle KB, and Local Workspace.
- Detects conflicting context and enforces multi-source evidence verification.
5. Confidence Engine (src/engine/confidenceEngine.ts)
- Computes Confidence Score % (0% - 100%), Quality Grade (A+ to D), and evidence diversity metrics.
- Flags missing context indicators to eliminate AI hallucinations.
6. Deep Root Cause Tracing Engine (src/engine/rootCauseEngine.ts)
- Recursive backtrace engine:
ORA / PLS Error→Package Invalid→View Compilation Failure→Missing Column/Table→Root Cause, Remediation & Verification.
7. Dependency Graph & Impact Analysis Engine (src/engine/dependencyGraphEngine.ts)
- Maps relationships across
Entity↔Projection↔Package↔View↔Table↔Custom Field↔Security Grants↔OData Endpoints. - Evaluates risk levels (
LOW,MEDIUM,HIGH,CRITICAL) and downstream callers before code edits.
8. Self-Validating Quality Gate & Static Analyzer (src/engine/qualityGateEngine.ts)
- Evaluates code against SOLID principles, Cust-layer customization rules, missing
initialcheck implementation;declarations, rawCOMMITinside PL/SQL LUs, and SQL injection risks.
🛠️ 76 Specialized MCP Tools Across 14 Categories
| Category | Key MCP Tools |
|---|---|
| Copilot & Orchestration | copilot_orchestrated_query, analyze_impact, trace_root_cause, evaluate_quality_gate, evaluate_consensus_confidence |
| Documentation & RAG | search_docs, compare_version_docs, related_docs, search_examples |
| Code & Test Generation | generate_unit_test, generate_bulk_plsql, generate_autonomous_transaction, generate_plsql, generate_package, generate_entity, generate_projection, generate_page |
| Oracle DBA & Tuning | oracle_dba_help, explain_execution_plan, analyze_schema, find_table, find_view |
| Reporting & SSRS | generate_xml_report_writer, generate_rdf, generate_rdl, generate_report_parameters |
| Code Review & Quality | review_code, review_architecture, detect_code_smells |
| Oracle Error Diagnosis | explain_ora_error, suggest_fix, explain_plsql_error |
| Integration & REST | generate_rest_api, test_rest_endpoint, generate_ifs_connect_routing |
| Security & Grants | audit_security, grant_projection_access |
| Marble DSL | validate_model, parse_entity, parse_projection, parse_client |
| Workspace & Indexing | index_workspace, search_workspace |
🌐 Universal 100% Local-Independent Cloud Connection
Your MCP Server is running 24/7 on Render cloud:
- Cloud SSE Endpoint:
https://ifs-mcp-server.onrender.com/sse - Cloud Telemetry Endpoint:
https://ifs-mcp-server.onrender.com/metrics - Cloud Health Endpoint:
https://ifs-mcp-server.onrender.com/health - OpenAPI Schema for ChatGPT:
https://ifs-mcp-server.onrender.com/openapi.json
1. Claude Desktop
Copy clients/claude_desktop_config.json to %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"ifs-developer-intelligence": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://ifs-mcp-server.onrender.com/sse"]
}
}
}
2. Cursor IDE
Add new MCP Server in Cursor Settings:
- Type:
command - Command:
npx -y mcp-remote https://ifs-mcp-server.onrender.com/sse
3. VS Code / Windsurf
Use clients/vscode_mcp.json or clients/windsurf_mcp.json:
{
"mcpServers": {
"ifs-developer-intelligence": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://ifs-mcp-server.onrender.com/sse"]
}
}
}
4. ChatGPT (Web Actions / Custom GPTs)
Import Action Schema from URL: https://ifs-mcp-server.onrender.com/openapi.json.
⚙️ Local Development & Testing
# Install dependencies
npm install
# Build TypeScript
npm run build
# Run Vitest test suite (12 tests)
npm test
# Run HTTP / SSE Server locally
npm run start:sse
🛡️ License
MIT License. Built for Enterprise IFS Cloud Development & AI Architecture.
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.