LF Energy Summit Europe 2026

Executing grid modelling and simulations like load flows, N-1 analyses, or sensitivity studies typically demands deep tooling expertise or custom scripting. What if grid engineers could drive these workflows directly in natural language - without sacrificing rigor or control?

pypowsybl-mcp demonstrates an open-source Model Context Protocol (MCP) server that exposes PowSyBl as AI-callable tools, callable by any conversational UI or AI agent to perform grid modelling simulations.

Our demo showcases a comprehensive TSO workflow driven entirely by natural-language prompts. Attendees will watch our AI agent dynamically orchestrate complex tool calls to execute:
1. Stress assessment: "Run an AC load flow; show voltage violations"
2. N-1 security: "Run N-1 on 400 kV lines; identify insecure contingencies"
3. Sensitivity: "Rank generators by impact on overload mitigation"
4. Remedial action: "Re-dispatch and re-run N-1"
5. Reproducibility: "Generate a Python script to reproduce this session"
Results come from pypowsybl (accurate, reproducible, hallucination-free results), while the LLM handles orchestration only and adaptation of results to the expertise of the user.