openPASO MCP server
Commit Nov 13, 2026Lets an AI model run nine finite-element and multiphysics codes by describing physics problems in plain language.
Also known as open-PASO/openPASO
- Stars
- 29
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 13, 2026
- License
- MIT
What is openPASO MCP?
openPASO lets an AI model run nine finite-element and multiphysics codes by describing physics problems in plain language.
Summary generated from the project's README
About openPASO MCP server
openPASO provides an interface for AI models to interact with nine different finite-element and multiphysics solvers. Instead of manually writing complex input files for various simulation programs, a user can describe a physics problem using natural language. The system then selects the appropriate solver, generates the necessary input, executes the simulation, and verifies the results.
This MCP server runs locally via stdio and requires Python 3.10 to 3.13. It can be integrated with existing AI applications like Claude Desktop or Cursor, or used with an OpenRouter key for custom model access. The server includes tools such as setup_backend to manage solver installations and a doctor command to check available capabilities on a machine. Supported solvers include scikit-fem, NGSolve, Kratos Multiphysics, DUNE-fem, FEniCSx, deal.II, FEBio, 4C Multiphysics, and SPARTA.
What you can do with it
- 1Automated physics simulationAsk an AI to simulate how a specific part bends or how heat spreads through a material.
- 2Solver management and installationUse the server to identify which simulation engines are currently installed on your local machine.
- 3Natural language problem modelingProvide a plain text description of a physical phenomenon to have the AI generate the simulation setup.
- 4Automated solver configurationRequest the installation of a specific missing solver like ngsolve through the server tools.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableopen-paso/openpaso is public and reachablegithub.com/open-paso/openpaso ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/open-paso/openpaso ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub[!WARNING] openPASO is under active development, and we invite you to help. It works and is used for real simulations, but it is young: things change quickly and you will find rough edges. Try it, tell us what broke, and share what you know about a solver. See Contribute.
What it does
Simulation programs, called solvers, compute how things physically behave: how a part bends, how heat spreads, how air flows. They are powerful and hard to use, and each one has its own input format and its own traps. openPASO puts nine of them behind one door and lets an AI model open it: you describe what you want in a normal sentence, and the model picks a solver, writes the input, runs it, and checks that the answer is computed correctly.
Quick start
You need Python 3.10–3.13 and about ten minutes. One solver is enough to begin.
pip install openpaso # the server, with scikit-fem as a first solver
openpaso doctor # which solvers openPASO can use on this machine; no key, no network
openpaso # starts the MCP server on stdio; Ctrl-C to stop
Missing a solver? openpaso install ngsolve (or kratos, dune, ...) checks first and installs only
what is missing, the same way the server's setup_backend tool would.
openpaso is the command your AI app's MCP configuration points at. Working from a checkout
instead (to change the code, or to run check_install.py, which lists the solvers openPASO can
use on your machine without a key or network):
git clone https://github.com/open-PASO/openPASO.git
cd openPASO
python3 -m venv .venv && source .venv/bin/activate
pip install -e . scikit-fem
python check_install.py
Then connect an AI model, one of two ways:
- Option A — an AI app you already have (Claude Code, Claude Desktop, Cursor): no extra cost. Set it up →
- Option B — your own OpenRouter key: one command per simulation, any model. Set it up →
Solvers
| scikit-fem | NGSolve | Kratos Multiphysics |
| DUNE-fem | FEniCSx | deal.II |
| FEBio | 4C Multiphysics | SPARTA |
Documentation
Everything else is on the documentation website: installing each solver, both ways of use step by step, all 24 tools the model gets, how openPASO checks an answer, coupling two solvers on one problem, troubleshooting, and a glossary for every word.
Contribute
Reports of what did not work, solver traps you know, and plain-language fixes to the documentation are all very welcome. One rule stands above the rest: every improvement must help all simulations, not one example. See CONTRIBUTING.md and the Contribute page.
Licence and citation
MIT licence. openPASO was first published as OASiS; the archived releases and the paper use that name. If you use openPASO in research, please cite:
@software{openpaso2026,
title = {openPASO: an open-source multi-physics and multi-code framework
for verified computer simulations},
author = {Hermann, Alexander and Shojaei, Arman and Scheider, Ingo and Cyron, Christian},
year = {2026},
doi = {10.5281/zenodo.20543501},
url = {https://github.com/open-PASO/openPASO}
}
openPASO MCP questions
What can openPASO do?
It allows an AI model to pick a solver, write its input, run it, and check the answer based on a plain-language description of a physics problem.
Which solvers are supported?
The platform supports nine solvers including scikit-fem, NGSolve, Kratos Multiphysics, DUNE-fem, FEniCSx, deal.II, FEBio, 4C Multiphysics, and SPARTA.
How do I install a missing solver?
You can use the command openpaso install <solver_name> to check for and install missing solvers.