Infragistics Blog - AI Engineering
Ignite UI CLI 15 – MCP Server, ai-config & Blazor Scaffolding
Ignite UI CLI 15 (releases 15.0.0 through 15.5.0) turns the CLI into the setup layer of the Ignite UI AI-assisted development toolchain. Highlights: the Ignite UI CLI MCP server with documentation and API lookup for AI assistants across Angular, React, Web Components, and Blazor; the ai-config command for one-command Agent Skills and MCP configuration; Blazor project scaffolding via dotnet new igb-blazor; and modernized Angular templates on signals and Angular 22. CLI 15.0.0 removes the legacy igx-ts-legacy, ig-ts, and igr-es6 project types.
Ignite UI MCP Testbed: An Open-Source Bench for Measuring What Your AI Agent's Tooling Actually Does
The Ignite UI MCP Testbed is a free, open-source end-to-end testing suite that runs one shared prompt across a matrix of supported platforms, AI models, and tooling variants, then lets you compare the results side by side. It currently covers web app generation tests against Angular, React, Blazor, and Web Components. Every run can include scenario-specific Playwright verification tests. No account, no license, no breaking changes - clone it and run your first test matrix today and evaluate how your AI agent skills and MCP servers perform.
MCP vs RAG: AI Documentation Retrieval Benchmark
MCP vs RAG is the central tradeoff this report measures: retrieval-augmented generation over a static vector index is the default architecture for AI documentation assistants, but it degrades silently as source documentation changes faster than the index is rebuilt. This report benchmarks that architecture against a Model Context Protocol (MCP) server that queries Ignite UI documentation and API definitions, using Anthropic Claude as the orchestrating model in both configurations.
MCP vs RAG: 100-Query Benchmark Reveals the Costly Winner
MCP vs RAG: MCP-based retrieval beats a vector-indexed RAG on grounding and citation depth, but it's slower and more expensive. Use it for correctness-critical requests; keep RAG for high-volume, latency-sensitive ones.
Why AI Results Improve Over Time, Not Model Learning
AI results improve over time even when the model never changes - context accumulation across your dev stack. Run a clean-room test to measure your true baseline.
Why Ignite UI AI Tooling Produces Better Results: MCP vs. No-MCP Benchmarks
Seven paired benchmarks against Ignite UI for Blazor and Angular show what MCP servers and Agent Skills change in AI-assisted development: component compliance rises from 0/5 to 5/5 in every scenario where the untooled model ignored the library, single-prompt feature completion rises from 71% to 100%, and total session cost including corrections is equal or lower.