Schema-Bound LLM Control of Scientific Instrumentation through Model Context Protocol Skills
On the map: LLM agents and tool use → Tool learning and function calling
Abstract (arXiv)
Large language models (LLMs) can plan tool-mediated scientific work, but scientific instruments remain difficult to connect to such agents: vendor APIs may load only inside acquisition host processes, facilities may prohibit cloud-hosted agents, and natural-language interfaces can emit physically unreasonable arguments. We present a method for connecting local LLMs to scientific instruments through the Model Context Protocol (MCP). It combines: (1) a schema-bound tool surface that validates requests against physical bounds before adapter dispatch; (2) a vendor-neutral, host-process adapter pattern separating language-side reasoning from instrument-side execution; (3) a persistent lifecycle for long-running live-processing jobs; and (4) MCP-prompt-registered skills that compose typed tools into reusable multi-step protocols. Our open-source reference server exposes 30 typed tools, 5 live-job types, and 6 skills through a physics-plausible simulator implementing the same protocol surface. Validation is software-only: all 120 hardware-independent tests pass deterministically, while 15 local-LLM integration tests pass 12-15 of 15 across runs because of model nondeterminism. A preliminary single-run probe across five open tool-calling LLMs indicates that the schema-bound interface can be driven locally by small open-weight models without cloud dependency; it is not a benchmark and has no confidence intervals. The method provides a bounded, testable, and reproducible foundation for closed-loop agentic instrumentation research.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 12 of its 42 references that are in the map. First posted on arXiv 19 Jul 2026.
Builds on
12 of 42 references.
Closest ancestors · 1
Same direction, newest first
Other references · 11
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
- 2025Accelerating scientific discovery with Co-Scientistcited by 353
- 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
- 2025An AI system to help scientists write expert-level empirical softwarecited by 52
- 2021AtomAI: A Deep Learning Framework for Analysis of Image and Spectroscopy Data in (Scanning) Transmission Electron Microscopy and Beyondcited by 19
- 2025LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodologycited by 10
- 2026Audit Trails for Accountability in Large Language Modelscited by 10
- 2025Experiences with Model Context Protocol Servers for Science and High Performance Computingcited by 6
- 2026Large Language Model Agent for User-friendly Chemical Process Simulationscited by 5
- 2026R-LAM: Reproducibility-Constrained Large Action Models for Scientific Workflow Automationcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
- 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents
- 2025MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
- 2025Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling
- 2026Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows
- 2026Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
- 2026Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance
- 2026ToolGate: Contract-Grounded and Verified Tool Execution for LLMs