MCP overview
Overview#
The Model Context Protocol (MCP) is an open-source standard which enables AI Large Language Models (LLMs) to seamlessly connect with external systems. MCP provides a unified way for LLMs to interact with tools, data sources, and workflows, similar to how REST APIs standardize client–server communication.
MCP support was introduced to the AI Service in Platform version 5.1.
Benefits of MCP#
MCP offers the following key features:
- Enables AI systems (such as Cursor and Claude) to access Platform resources within a namespace.
- Application developers can now expose their scripts as MCP tools, making them usable across any MCP-supported AI system.
- Makes tool usage structured and predictable.
- Reduces the need for custom integrations for each AI application.
Key MCP components#
MCP offers the key components listed below.
| Component | Description |
|---|---|
| Tools | Executable functions which the LLM can call |
| Resources | Files or data (text, binary, images) |
| Prompt Templates | Resumable templates for task execution |
AI Service support for MCP#
The AI Service supports MCP in three ways: