Glossary

Model Context Protocol

MCP

An open standard, released by Anthropic on November 25, 2024, that defines a client-server architecture for connecting AI applications to external data sources, tools, and prompts over JSON-RPC 2.0. IBM's IBM i MCP Server is an implementation of it for Db2 for i and other IBM i resources.

Short nameMCP
Released byAnthropic, November 25, 2024
Message formatJSON-RPC 2.0
IBM i versionThe IBM i MCP Server

How MCP connects AI to your systems

  1. The hostAn app such as Claude Desktop or an IDE runs an MCP client.
  2. The clientThe client talks to one or more MCP servers over JSON-RPC 2.0.
  3. The serversEach server exposes one system's data or actions through the same common interface.

The payoff: a developer writes one connector per system instead of a custom integration for every AI tool.

MCP reaches IBM i

  1. Nov 25, 2024Anthropic releases the Model Context Protocol.
  2. Mar 2025OpenAI adds MCP support across its Agents SDK, Responses API and ChatGPT desktop.
  3. Jun 2025Profound Logic adds MCP support to Profound AI.
  4. Oct 27, 2025IBM opens the IBM i MCP Server in beta.
  5. Apr 2026IT Jungle reports ARCAD's plan to launch the ARCAD MCP Server.

Where MCP shows up on IBM i

  • IBM i MCP Server, from IBM
  • ARCAD MCP Server, from ARCAD Software
  • Profound AI, from Profound Logic
  • Rocket DevOps AI MCP interfaces, from Rocket Software
  • IBM Bob, whose tool calling relies on the same protocol

Related Terms

IBM i MCP Server

An open-source, IBM-published server implementing the Model Context Protocol (MCP), letting AI agents and LLMs query Db2 for i data and take defined actions on IBM i using natural language. In beta since October 2025.

Mapepire

An open-source database access layer for Db2 for i, created by IBM and introduced in an August 2024 IBM blog post as a lighter, cloud-friendly alternative to ODBC and JDBC. A server daemon runs on IBM i and Node.js, Python, Java, and .NET Core clients connect to it over Secure WebSockets.

Large Language Model (LLM)

A machine learning model trained on large volumes of text, used as the underlying technology behind generative AI tools including IBM Bob and general-purpose assistants like ChatGPT and Claude.
Back to Glossary