NIMO Controller: a self-driving laboratory orchestrator based on the Model Context Protocol
Quick Answer
The NIMO Controller is a self-driving laboratory orchestrator utilizing the Model Context Protocol (MCP) to streamline experimental workflows for both human users and AI agents.
Quick Take
It features a visual programming interface that eliminates the need for coding, enhancing accessibility for scientific discovery. A case study on color-matching demonstrates the system's usability and effectiveness.
Key Points
- NIMO Controller exposes SDL functionalities through servers for better integration.
- The visual programming interface allows users to design workflows without coding.
- AI agents can access the same MCP backend, ensuring a unified interface.
- A case study validates the architecture's usability in a color-matching SDL.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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, allowing human users to design experimental workflows without writing code. The same MCP backend can also be accessed by AI agents, providing a unified interface for both human users and AI agents. We demonstrate the proposed system through a case study on a color-matching SDL. The results validate the usability of the proposed MCP-based SDL architecture.
| Comments: | 9 pages, 4 figures |
| Subjects: | Artificial Intelligence (cs.AI); Materials Science (cond-mat.mtrl-sci); Robotics (cs.RO) |
| Cite as: | arXiv:2605.15227 [cs.AI] |
| (or arXiv:2605.15227v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15227 arXiv-issued DOI via DataCite |
Submission history
From: Naruki Yoshikawa [view email]
[v1]
Wed, 13 May 2026 14:25:45 UTC (2,809 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.