https://shaaf.dev/tags/gen-llm/Recent content in Gen-LLM on Shaaf's blogHugoen-usThu, 08 Jan 2026 00:00:00 +0000https://shaaf.dev/post/2026-01-08-two-essential-patterns-for-buildingm-mcp-servers/Thu, 08 Jan 2026 00:00:00 +0000https://shaaf.dev/post/2026-01-08-two-essential-patterns-for-buildingm-mcp-servers/<p>When building Model Context Protocol (MCP) servers, I learned two critical design patterns the hard way. What started as a straightforward implementation of a Keycloak administration server quickly became unwieldy—until I discovered <strong>Intent Multiplexing</strong> and the <strong>Command Pattern</strong>. Together, these patterns transformed a maintenance nightmare into an elegant, extensible architecture.</p> <p>This post shares those lessons so you can avoid the same pitfalls.</p> <p>Replicate each operation from your API and viola! you have a tool explosion. And that might not seem evident in the first place, but becomes a serious problem. An LLM might not be able to handle that large context, it might even start to halluncinate.</p>