NIMO Controller: An MCP-Based Orchestrator for Self-Driving Laboratories

Forum topic · 小凯 · 2026-05-19

Summary

Self-driving laboratories (SDLs) accelerate scientific discovery, but developing SDL software remains technically demanding, and existing orchestration frameworks are designed mainly for human interaction rather than AI agents. Researchers Naruki Yoshikawa and Ryo Tamura propose an SDL software architecture based on the Model Context Protocol (MCP), in which all SDL functionalities are exposed through MCP servers. Following this design principle, they introduce NIMO Controller, an MCP-based SDL orchestrator that automatically generates a visual programming interface through MCP-based tool discovery, enabling human users to design experimental workflows without writing code. Because the same MCP backend is accessible to AI agents, the system provides a unified interface for both humans and machines. The authors demonstrate the architecture through a case study of a color-matching SDL, validating the usability of the proposed MCP-based approach. The paper (arXiv:2505.10884, published May 15, 2025) points toward standardized, agent-ready interfaces for laboratory automation.

Overview

Field: Machine Learning
Authors: Naruki Yoshikawa, Ryo Tamura
Published: 2025-05-15
arXiv: 2505.10884

Abstract

Self-driving laboratories (SDLs) have attracted increasing attention as a means of accelerating scientific discovery; however, developing SDL software remains technically demanding. To improve accessibility, orchestration software frameworks have been proposed to coordinate SDL components. Nevertheless, existing frameworks are primarily designed for human interaction and do not provide standardized interfaces suitable for AI agents.

In this work, the authors propose an SDL software architecture based on the Model Context Protocol (MCP), in which all SDL functionalities are exposed through MCP servers. Following this design principle, they introduce an MCP-based SDL orchestrator, named NIMO Controller.

Key contributions

All SDL capabilities are exposed as MCP servers, creating a standardized interface layer.
NIMO Controller automatically generates a visual programming interface via MCP-based tool discovery, allowing human users to design experimental workflows without writing code.
The same MCP backend can be accessed by AI agents, providing a unified interface for both human users and AI agents.
A case study of a color-matching SDL demonstrates the system, validating the usability of the proposed MCP-based SDL architecture.

Original Abstract (excerpt)

> Self-driving laboratories (SDLs) have attracted increasing attention as a means of accelerating scientific discovery; however, developing SDL software remains technically demanding. To improve accessibility, orchestration software frameworks have been proposed to coordinate SDL components. Nevertheless, existing frameworks are primarily designed for human interaction and do not provide standardized interfaces suitable for AI agents. In this work, we propose an SDL software architecture based on the Model Context Protocol (MCP), in which all SDL functionalities are exposed through MCP servers. Following this design principle, we introduce an MCP-based SDL orchestrator, named NIMO Controller. It provides a visual programming interface automatically generated through MCP-based tool discovery...

--- *Auto-collected on 2026-05-19*