Posts

Robust X++ class skeleton - AI Custom API

Image
  Robust X++ class skeleton - AI Custom API This template demonstrates how to structure the class, define the input parameters (Data Contract), and implement the logic required for the invoke_action tool to function. X++ Developer Starter Kit: AI Custom API This example assumes you are building a tool to "Check Inventory Stock" directly via code. 1. The Data Contract (The Input) First, define what information the AI Agent needs to send you. This uses standard D365 F&O Data Contracts. [DataContract] public class MyInventoryCheckContract {     str itemId;     str siteId;       [DataMember("ItemId"), SysOperationLabel("Item ID"), SysOperationHelpText("The identifier for the product to check.")]     public str parmItemId(str _itemId = itemId)     {         itemId = _itemId;         return itemId; ...
Post a Comment
Read more

Exposing A Custom Class to Dynamics 365 MCP Server

Image
  Breaking the Forms: Direct Code Invocation for Agents in Finance & Operations Apps Most AI agents interacting with enterprise ERPs—like Microsoft Dynamics 365 Finance & Operations—operate like super-fast human users. They navigate forms, click buttons, and fill in fields. This "form interaction" pattern is powerful because it instantly makes millions of existing UI-based actions available to your AI. But what if the business logic you need isn't on a form? Or what if navigating a complex wizard is too slow and fragile for a critical backend process? This is where the find_actions and invoke_action tools shine. They allow developers to bypass the UI layer entirely and expose direct code execution to the Model Context Protocol (MCP) server. The "Escape Hatch": Direct Code Access While standard MCP tools rely on form metadata, find_actions and invoke_action are special. They act as a bridge directly to your application's X++ classes. f...
Post a Comment
Read more

Unlocking AI Agents in Dynamics 365 ERP: A Deep Dive into the New MCP Server Tools (Part 2)

Image
  Unlocking AI Agents in Dynamics 365 ERP: A Deep Dive into the New MCP Server Tools (Preview) The era of AI agents in ERP is here. With the introduction of the Dynamics 365 ERP MCP (Model Context Protocol) server , developers and architects now have a bridge between natural language prompts and concrete actions within Finance and Operations (F&O) apps. But how does the agent actually "drive" the application? The magic lies in the Agent Orchestration layer, which uses a specific set of tools to translate a user's intent (e.g., "Filter the vendor list by New York") into technical commands the ERP understands. In this post, we’ll break down the standard toolkit available in the preview and explore how developers can extend these capabilities with custom code. The Standard Toolkit: Interacting with Forms The majority of the tools in the MCP server are designed to simulate user interactions. They allow the agent to navigate menus, fill out fields, and manipulat...
Post a Comment
Read more

Dynamics 365FO is going Agentic, meet the Model Context Protocol (Part 1)

Image
Dynamics 365FO is going Agentic, Meet the Model Context Protocol (Part 1). Unlock the Power of AI in Your ERP: Meet the Model Context Protocol (MCP) If you work with Dynamics 365 Finance and Operations, you know that integrating AI tools can sometimes feel like a heavy technical lift. You typically need custom APIs, complex connectors, and extensive code. Microsoft is changing that with the Model Context Protocol (MCP) . This new standard is designed to let AI agents (like Microsoft Copilot) "talk" to your ERP system just like a human would. Here is a breakdown of what MCP is and why it matters, in plain English. What is MCP? Think of MCP as a universal translator between your AI agents and your business data. It is an open standard that helps AI understand the context of your data in Dynamics 365. Instead of building a custom bridge for every single task you want an AI to do, MCP provides a standard highway. It enables AI agents to securely access your data and business logi...
Post a Comment
Read more