Signal Index · Vol. 3 · March 15, 2026

The Architecture Signal

The bridge is built. The stack is named. Four layers, all available today. The IBM i platform is not behind the AI era — in a meaningful architectural sense, it anticipated it.

Reggie Britt · signal4i.ai · T  O

The version that's over

The Bridge Is Built. The Stack Is Named.

There is a version of this moment where the IBM i community spends the next three years watching AI happen to other platforms. That version is over.

IBM has built the bridge. The stack is named. The tools are available today. And the people best positioned to use them are the ones who already know the business the stack is built to run.

This issue is about the architecture. Not a roadmap. Not a beta. What exists right now, how the layers connect, and why this platform is not behind — it is ahead of where every other enterprise stack is trying to get.

Signal 09 · The Protocol Signal

MCP — The Bridge Has a Name. It's Live.

Signal 09 · IBM · Oct 2025 → 2026
IBM releases the IBM i MCP Server
Tech preview: TechXchange 2025 · Production-ready: 2026 · 500 tools targeted
"Our team has made an initial version of an IBM i MCP server available, and we've set a goal to produce at least 500 tools in 2026." — IBM i MCP Server documentation

For years, the practical barrier to connecting IBM i to the modern AI ecosystem wasn't the data or the logic — it was the interface. Model Context Protocol changes that. MCP is the tool protocol — the layer that defines what an agent is authorized to access, execute, and observe. Anthropic designed it as a universal standard, a USB-C port for AI applications. One protocol. Any agent. Any framework.

IBM shipped the IBM i MCP Server under an Apache 2.0 open source license. SQL Services. CL Commands. System monitoring. Security auditing. All exposed as callable tools to any MCP-compatible agent. The supported client list: Claude Code, Claude Desktop, VSCode, Cursor, Windsurf, Roo Code, LM Studio, Gemini CLI, Cline. IBM is building for the whole ecosystem.

Signal 10 · The API Signal

Mapepire — The Db2 You Already Have, Now Callable

Signal 10 · IBM · 2024–2025
Mapepire ships as IBM's open-source Db2 access layer
Production confirmed · LangChain, Agno, MCP · Seiden Group July 2025
"Mapepire bridges the gap by providing a modern, WebSocket-based SQL query interface that's optimized for the request/response patterns of AI agents and MCP tools." — IBM i MCP Server documentation

The fear that stopped most IBM i modernization conversations was legitimate: you can't touch what's running. Mapepire is different. It sits above the Sovereign Core — RPG and Db2 stay exactly as they are. Mapepire makes them callable via WebSocket, optimized for the request-response patterns AI agents actually use.

Multiple agentic frameworks are confirmed working with IBM i via Mapepire: LangChain, Agno, and the MCP protocol itself. BeeAI and CrewAI are in progress. The ecosystem is not locked to a single vendor or approach. The IBM i MCP Server requires Mapepire as its foundation. They are not separate tools — they are the two layers of the same bridge.

Signal 11 · The Stack Signal

The Four Layers — All of Them Exist Today

Layer 1 — The Sovereign Core
RPG and Db2. Untouched.
Thirty years of business logic, transaction integrity, and operational reliability. This is the moat. It doesn't move. No competitor can buy it. No migration preserves it.
Layer 2 — The API Layer
Mapepire. Node.js on PASE.
The Sovereign Core becomes callable. Business logic and Db2 data exposed over modern interfaces without disturbing production operations. The bridge runs alongside the system — not through it.
Layer 3 — The Agentic Layer
Python orchestration. LangChain or Agno.
An Orchestrator Agent that routes, plans, and reasons. Specialist agents that execute. The MCP protocol bridge connects agents to the tools they're authorized to use. The Think → Act → Observe loop runs against your own data, in your own environment, under your own governance.
Layer 4 — The Modern Surface
React or Next.js.
Business users interact with the system through an interface that speaks their language. Configuration in hours, not tickets. System behavior changes without requiring a development cycle. The prompt is the interface.
Signal 11 · IBM · 2025–2026
The complete IBM i agentic stack specified and demonstrated
"Each layer has a distinct responsibility. MCP is the protocol bridge, not the orchestrator. Nothing bleeds across the boundary." — IBM i Agentic Architecture
Signal 12 · The Native Signal

The Stack Is Still Expanding

IBM is developing an experimental SDK that would let developers call AI models directly from Db2 for i — and by extension from RPG via embedded SQL. The concept: a SQL function call connects existing business logic to any LLM endpoint. IBM watsonx, Ollama, any OpenAI-compatible solution, on-premise inference options — all reachable from inside the RPG codebase itself. No new language. No new architecture layer.

The SDK is currently documented as experimental. IBM's own GitHub describes it as "in bringup state." But the direction is clear: if this ships, existing RPG code participates in AI workflows without a rewrite. The 30 years of business logic encoded in that codebase doesn't have to be migrated, translated, or replaced to become part of an agentic system. It calls the agent. The agent calls it back.

What this means

Four signals. One conclusion. The IBM i MCP Server is live and in active development. Mapepire is the foundation multiple frameworks already run on. The four-layer stack is specified and deployable today. And IBM is building the next layer — native AI calls from RPG — with production readiness on the horizon.

What's missing is not technology. It is not the platform. It is not the people. What's missing is the posture. The organizational decision to treat this as the moment it is — and to move before someone else names what you have and builds on top of it without you.

← Vol. 2 · The Posture Problem
Signal Index · Vol. 1–8 arc
Full archive →