"author:gDupuis61" matching MCP servers:

Enables analysis of documents far larger than an LLM's context window without vector databases or chunking, by having the model emit constrained Nucleus S-expression commands that the Lattice engine parses, type-checks, and executes against the document. Handle-based in-memory storage, a server-side memo pad, and recursive sub-query primitives let agents work with compact stubs instead of large text blobs.