Sponsored by Deepsite.site

Pega DX MCP

Created By
MarcoLooy7 months ago
This MCP Server transforms Pega Infinity™ interactions into intuitive, conversational experiences through the Model Context Protocol. By bridging Pega DX APIs with natural language interfaces, it enables GenAI Agents, IDEs, and other MCP-enabled tools to interact with Pega Infinity™ applications using simple, human-readable commands.
Content

Pega DX MCP Server

Pega DX MCP Server

License Node.js MCP Pega Platform

Enabling conversational interaction with Pega Infinity™ Applications

This package transforms Pega Infinity™ interactions into intuitive, conversational experiences through the Model Context Protocol. By bridging Pega DX APIs with natural language interfaces, it enables GenAI Agents, IDEs, and other MCP-enabled tools to interact with Pega Infinity™ applications using simple, human-readable commands.

🧪 Experimental

The Pega DX MCP Server is an experimental project exploring the intersection of Model Context Protocol and Pega Infinity™ capabilities. This is not an official Pegasystems product and is not generally available. All commands, parameters, and other features are subject to change or deprecation at any time, with or without notice. Do not use this MCP server for production functionality. This experiment demonstrates the potential of natural language interfaces for Pega Infinity™ interactions. We welcome feedback and contributions to help shape the future of GenAI-powered business automation.

🌟 Key Features

  • 🤖 Natural Language Interface - Demonstrates conversational case creation: "Create a travel claim for John"
  • 🔌 Plug-and-Play Integration - Experimental compatibility with GenAI Agents, IDEs, and MCP-enabled tools
  • 🧪 Innovation Prototype - Exploring enterprise-grade patterns with comprehensive error handling approaches
  • 📡 API Integration Exploration - Investigating access to cases, assignments, attachments, and data operations
  • ⚡ Performance Research - Experimenting with intelligent caching and optimization strategies
  • 🛡️ Security Framework - Implementing OAuth 2.1 with PKCE and role-based access control patterns

🚀 Quick Start

Prerequisites

  • Node.js (22+) and npm
  • Access to Pega Infinity™ (23+) with DX API enabled
  • OAuth 2.1 client credentials

Installation

# Install from npm (recommended)
npm install -g @pega-enablement/pega-dx-mcp

Integration with MCP Clients

Compatible with Claude Desktop, Cursor, Cline, and other MCP-enabled applications. Add to your MCP client's configuration file:

{
  "mcpServers": {
    "pega-dx-mcp": {
      "command": "npx",
      "args": ["-y", "@pega-enablement/pega-dx-mcp"],
      "env": {
        "PEGA_BASE_URL": "https://your-pega-instance.com",
        "PEGA_CLIENT_ID": "your-client-id",
        "PEGA_CLIENT_SECRET": "your-client-secret"
      }
    }
  }
}

Configuration file locations:

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows)
  • Cursor: .cursor/mcp.json in your project root
  • Cline: MCP settings in VS Code

Verify installation: Restart your MCP client and confirm the Pega DX tools are available.

🏗️ Architecture

The Pega DX MCP Server bridges GenAI applications with Pega Infinity using the Model Context Protocol:

Pega DX MCP Server Architecture

🛠️ Available Tools

Case Management

ToolDescriptionExample Usage
get_caseGet detailed information about a Pega case by ID"Show me details for case TRAVEL-001"
create_caseCreate a new Pega case with specified case type"Create a travel claim for John to NYC"
delete_caseDelete a case that is currently in create stage"Delete case TRAVEL-001"

System Management

ToolDescriptionExample Usage
ping_pega_serviceTest OAuth2 connectivity to Pega Platform"Test the connection to Pega"

💬 Usage Examples

Note: The following examples demonstrate envisioned capabilities and planned user experiences. These scenarios represent the experimental goals of this GenAI Innovation project and may not reflect current implementation status.

Creating a Case

User: "Create a new insurance claim for policy #12345"
AI: I'll create a new insurance claim case. What type of claim is this?
User: "Auto accident claim"
AI: ✅ Created auto accident claim case INS-CLAIM-789
    Case ID: INS-CLAIM-789
    Policy: #12345
    Status: Open
    Next step: Provide accident details

Managing Assignments

User: "What's my next assignment?"
AI: You have 3 pending assignments:
    1. Review claim documentation (INS-CLAIM-789) - Due today
    2. Approve travel request (TRAVEL-456) - Due tomorrow
    3. Customer callback (SERVICE-123) - Due in 2 hours
User: "Let me work on the claim review"
AI: ✅ Opening claim documentation review for INS-CLAIM-789
    [Displays relevant case data and required actions]

⚙️ Configuration

Environment Variables

# Pega Infinity Connection
PEGA_BASE_URL=https://your-pega-instance.com

# OAuth 2.1 Authentication
PEGA_CLIENT_ID=your-oauth-client-id
PEGA_CLIENT_SECRET=your-oauth-client-secret

OAuth Setup

  1. Register OAuth Client in your Pega Platform
  2. Configure Scopes for API access
  3. Set Redirect URIs if using authorization code flow
  4. Update Environment with client credentials

For detailed setup instructions, see our Configuration Guide.

🤝 Contributing

Join us in this exciting GenAI Innovation experiment! As an experimental project exploring the future of natural language interfaces for enterprise platforms, we welcome community participation in shaping this innovation journey.

Ways to Contribute

  • 🔬 Experiment Feedback - Share your experiences and insights from testing the prototype
  • 💡 Innovation Ideas - Contribute to the GenAI Innovation roadmap with creative suggestions
  • 🐛 Issue Reports - Help identify challenges in this experimental project
  • 🔧 Code Contributions - Contribute to the codebase and proof-of-concept features
  • 📖 Documentation - Help document learnings and experimental outcomes
  • 🧪 Testing & Validation - Participate in testing new experimental capabilities

Development Setup

# Fork and clone the repository
git clone https://github.com/your-username/pega-dx-mcp.git
cd pega-dx-mcp

# Install dependencies
npm install

# Create a feature branch
git checkout -b feature/your-feature-name

# Make changes and test
npm test

# Submit pull request

Guidelines

  • Follow our Code of Conduct
  • Ensure tests pass and add new tests for features
  • Update documentation for any API changes
  • Use conventional commit messages

📄 License

Licensed under the Apache License, Version 2.0. See LICENSE for details.


Built with ❤️ by Pegasystems

WebsiteCommunityDocumentation

Server Config

{
  "mcpServers": {
    "pega-dx-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@pega-enablement/pega-dx-mcp"
      ],
      "env": {
        "PEGA_BASE_URL": "https://your-pega-instance.com",
        "PEGA_CLIENT_ID": "your-client-id",
        "PEGA_CLIENT_SECRET": "your-client-secret"
      }
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
WindsurfThe new purpose-built IDE to harness magic
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Playwright McpPlaywright MCP server
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
ChatWiseThe second fastest AI chatbot™
DeepChatYour AI Partner on Desktop
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Tavily Mcp
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
Amap Maps高德地图官方 MCP Server
Serper MCP ServerA Serper MCP Server
CursorThe AI Code Editor