pandapower is covered by PowerMCP, where it is part of the base install: its server builds or loads networks, runs Newton-Raphson or backward/forward-sweep power flow and N-1/N-2 contingency analysis, and imports PSS/E, MATPOWER and other cases through PowerIO. A PowerSkills skill and its mitigation playbooks sit on top. Being a Python library, it runs anywhere Python does with no licence, and its developers publish no AI tooling of their own.
One Python package with separate MCP servers for pandapower, PyPSA, OpenDSS, PowerWorld, PSS/E, PowerFactory, PSCAD and more.
Skills that tell an agent which PowerMCP tool to use first, plus ten mitigation playbooks for power-system study findings.
Listings are sorted by origin, then by recent activity. GitHub data is refreshed nightly. Nothing here is ranked.
An MCP server or skill can only do what pandapower lets programs do. pandapower exposes 2 automation interfaces:
pandapower is developed jointly by the University of Kassel's e2n department and Fraunhofer IEE. Its documentation covers the library and its analyses and doesn't mention an AI assistant, LLM features or an MCP server, so the integrations available are community projects such as PowerMCP rather than anything from the developers.
Checked 4 Nov 2026. Sources: pandapower documentation
Taken from the listings' own documentation. Check each listing for exactly what it supports.
The listings here document setup for Claude Code, Claude Desktop, Codex CLI and Cursor. Install steps, copied from each project's own documentation, are on each listing's page. Most pandapower integrations run on your own computer next to pandapower, so you need pandapower installed and licensed on the same machine unless the listing says otherwise.
Yes, the pandapower server in PowerMCP. It comes with the base pip install powermcp, alongside PyPSA and the PowerIO converter, and needs no other software.
Yes. The run_contingency_analysis tool runs N-1 or N-2 outages on lines and transformers, and PowerMCP's demo shows an LLM writing a contingency report from pandapower and PowerWorld results.
The PowerSkills repository has a pandapower skill that sets the order of work (load, inspect, solve, then contingencies) and points to mitigation playbooks for voltage, thermal and convergence problems.
Yes. PowerMCP's PowerIO server parses the source case once, and the pandapower tools load the result with load_network_from_any or load_network_from_json. You can apply typed what-if edits, such as an outaged branch, during the import.
AI-generated models, drawings and results must be checked by a qualified engineer before use.
Sources (checked 4 Nov 2026): pandapower documentation · PowerMCP pandapower server README · Power-Agent/PowerSkills README · pandapower product page
pandapower is developed by its own project (Open source (University of Kassel and Fraunhofer IEE)). Tresca is independent and not affiliated with or endorsed by the pandapower project.