Orchestrating Power Grid Studies with Multi-Agent AI and MCP Servers
arXiv:2607.14158
The paper proposes using multi‑agent AI and the Model Context Protocol to let large language models interact with power‑grid simulation tools, enabling agents to set up, run, and retrieve results from transmission system studies with human oversight.
Abstract
This position paper explores how Agentic AI and Model Context Protocol (MCP) can support power-grid studies in a Transmission System Operator (TSO) context. We focus on integrating Large Language Models with numerical simulation tools, structured workflows, and human supervision. We identify key industrial requirements for agent assisted grid studies and introduce pypowsybl-mcp, an MCP-based interface exposing selected capabilities of our simulation tool, pypowsybl to AI agents. This first step provides a testbed to study how agents can setup simulations, execute analyses, retrieve results, and interact with power-system simulators through standardized tool calls. We also discuss principles for human-in-the-loop, multi-agent workflows and outline an evaluation strategy combining technical metrics and practitioner feedback. The paper positions MCP-based tool integration as a step toward more interactive, auditable, and scalable grid-study environments.
Accepted to IJCAI AISE 2026 workshop