Lab assets as a queryable graph — 181 instruments, one entity graph, 10 MCP tools.

A Rust and React gateway that ingests laboratory assets from an asset platform's REST API, builds a semantic entity graph and index, and serves it through search, retrieval-augmented chat, an equipment view, an interactive graph, and a full Model Context Protocol surface — 10 tools, 2 resources, 5 code-generation prompts — consumable directly by Copilot and Claude. Desktop through Tauri, web through WebAssembly. Demonstrated on a 4,115-asset corpus.

Lab equipment data exists but is not reasonable over. Asking which instruments can run an assay and which are due for calibration means knowing where to look rather than knowing the question.

Architecturally the point is that it is a repointing, not a rebuild: the same ingestion, entity graph, ontology, retrieval and capability mesh moved from documents to equipment without redesign. The thesis is a data foundation, not a chatbot — the conversational surface is the demo, the entity graph and the capability mesh are the product.

No public URL — internal system.