MCP

Are you looking at all the new AI tools and wondering how you can connect them to your powerful, battle-tested APIs? You’re in the right place! In this walkthrough, we’ll enhance an existing Salesforce System API by implementing the Dual-Exposure Pattern. This is a fancy way of saying we’ll make your API “AI-ready” by adding a new, smart entry point for AI agents without breaking your existing RESTful interface. We will expose three core operations—create a case, get case details, and update a case—as discoverable AI tools, all from the comfort of Anypoint Code Builder. ...

Imagine a world where your AI applications can effortlessly connect to and use any tool or data source… without needing a deep dive into complex, custom API documentation every single time. Right now, connecting Large Language Models (LLMs) to the tools they need often looks like a tangled web of custom, brittle integrations. 🕸️ Every new tool requires another piece of unique code, creating a bottleneck that’s complex and prone to errors. ...

Connecting a Mule application to an MCP Server is a core task for building modern, AI-driven integrations. While the MCP Connector makes this process straightforward, a few key details can make the difference between a smooth implementation and a frustrating debugging session. Having gone through the process, I want to share the three most important lessons I learned to help you get it right the first time. Lesson 1: Your Server URI Must Be Exact When you first set up the MCP Client configuration, your immediate instinct might be to just enter the hostname of your deployed MCP server. This is a common pitfall. ...