"author:HorstMorales" 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 are validated and executed server-side, with large result sets and stashed context kept behind compact handle stubs rather than roundtripped as full text. Supports recursive sub-queries and memo storage so agents can search, filter, aggregate, and recall document content token-efficiently.