"author:gabriel65523" matching MCP servers:

Enables analysis of documents far larger than an LLM's context window by having the model emit constrained symbolic S-expression commands that a logic engine executes against server-side state. Results and agent context are held as compact in-memory handles and memos rather than roundtripped text, yielding large token savings and support for recursive sub-queries.

Gives coding agents real product screens as visual references, letting them search for a screen matching a layout, state, or interaction question and then pull the recorded colors, typography, components, and provenance behind it. It also surfaces fonts, icons, and animated icon materials alongside their licenses, and exposes the bundled design workflow as skill resources and prompts.