Atlas / MCP servers / hereon-institutems / openPASO

openPASOBLOCK

Name: openPASO
Author: hereon-institutems

mcp/hereon-institutems/openpaso

MCP server by hereon-institutems · 4c multiphysics · ai agents · computational mechanics · Audited 2026-10-09

openPASO (formerly OASiS): an MCP server that lets an AI model run nine finite-element and multiphysics codes, with curated knowledge, verified execution and cross-code coupling. Under active development; contributions welcome.

Verdict

BLOCK

Grade

Trust score

39 /100

Exposed tools

64 51r · 13w · 0d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

openPASO

open Platform for Agentic Simulation and Optimization

Describe a physics problem in plain words. An AI model picks a solver, writes its input, runs it, and checks the answer.

Click the film to watch it in full quality on the documentation website.

[!WARNING] openPASO is under active development, and we invite you to help. It works and is used for

Read from source at commit 678b3ab53bf0OBSERVED · 2026-10-09

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add openpaso-ui --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env CLAUDE_CODE_OAUTH_TOKEN=${CLAUDE_CODE_OAUTH_TOKEN} --env OPENROUTER_API_KEY=${OPENROUTER_API_KEY} -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "openpaso-ui": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "CLAUDE_CODE_OAUTH_TOKEN": "${CLAUDE_CODE_OAUTH_TOKEN}",
        "OPENROUTER_API_KEY": "${OPENROUTER_API_KEY}"
      }
    }
  }
}

Exposed tools (64)

51 read · 13 write · 0 destructive.

Tool	Risk	Description
`audit_results`	read	Check your OWN result files for the failures that most often sink a
`benchmark_poisson_cross_solver`	read	Quick benchmark: Poisson on unit square across all available solvers.
`benchmark_problem`	write	Run the same physics problem on all available backends and compare.
`browse_solver_tests`	read	Browse real test/example files from a solver
`build_source`	write	Run the build recipe (CMake + ninja, or pip install -e .) for a
`check_input`	read	Name the defects of an input deck or script BEFORE it runs: the setup checks the run
`check_simulation_quality`	write	Run quality checks on a simulation BEFORE running it.
`compare_solvers`	read	Compare results from multiple solver runs side by side.
`couple`	read	GENERAL partitioned multi-code coupling — works for ANY physics/coupling.
`couple_levels`	read	EVERY PRESCRIBED MESH LEVEL IN ONE CALL -- the same partitioned coupling as
`couple_precice`	read	GENERAL preCICE coupling of ARBITRARY codes/paradigms, end-to-end.
`coupled_solve`	read	LEGACY cross-solver coupling — FIXED toy geometries only. PREFER `couple`.
`deep_validate`	read	Deep validation of solver input — catches physics errors, not just syntax.
`developer`	read	Developer tools: architecture, source files, capabilities matrix.
`discover`	read	Discover available solvers and their capabilities.
`discover_sources`	read	Find source trees + binaries for every backend by scanning the
`ensure_source`	read	One-shot: discover → fetch if missing → optionally build if no
`examples`	read	Find and retrieve example input files from solver test suites.
`fetch_source`	read	Clone the canonical upstream source for a backend into
`generate_input`	read	Generate a complete, runnable input for a solver backend.
`generate_mesh`	read	Generate a mesh using Gmsh for non-trivial geometries.
`get_coupling_knowledge`	read	Complete knowledge for partitioned multi-code coupling via `couple`.
`get_example_input`	read	Retrieve a complete, runnable example input file.
`get_example_inputs`	read	Get working example input files for a given physics module.
`get_input_file_guide`	read	Get a comprehensive guide for writing input files for a solver.
`get_input_schema`	read	Get the full input schema for a solver
`get_job_status`	read	Check the status of a simulation job.
`get_module_info`	read	Get detailed information about a specific physics module on a specific solver.
`get_physics_knowledge`	read	Get domain knowledge for a physics module from a specific solver backend.
`get_precice_knowledge`	read	Complete knowledge for preCICE coupling via `couple_precice`.
`get_solver_architecture`	read	Get the source code architecture and extension points for a solver backend.
`get_solver_capabilities_matrix`	read	Get a comprehensive capabilities matrix across all available backends.
`get_solver_info`	read	Get detailed information about a specific solver backend.
`get_tsi_knowledge`	read	Get complete knowledge for thermo-structural interaction (TSI) coupling.
`list_jobs`	read	List all simulation jobs from this session.
`list_physics`	read	List all physics problems solvable by available backends.
`list_solver_source_files`	read	List source files matching a pattern in a solver
`list_solvers`	read	List all registered FEM solver backends and their availability status.
`list_template_variants`	read	List all available template variants for a solver and/or physics module.
`list_tutorials`	read	List available tutorial examples for a solver backend.
`parameter_study`	write	Run a parameter study: same simulation with different parameter values.
`plot_all_fields`	read	Generate PNG plots for ALL fields in a simulation result.
`plot_result`	read	Generate a publication-quality visualization of simulation results.
`post_process`	write	Extract field statistics from simulation results.
`prepare_simulation`	write	Prepare everything needed to set up a simulation — in ONE call.
`query_documentation`	read	Search solver documentation for a specific topic.
`read_solver_test_file`	read	Read the content of a specific test/example file from a solver.
`recommend_solver_for`	read	Recommend the best available solver for a given physics problem.
`rediscover_backends`	read	Probe the system for solver backends and report findings.
`reload_catalog`	read	Hot-reload the per-backend KNOWLEDGE dicts from disk.
`restart_simulation`	write	Restart a completed simulation from its last checkpoint.
`run_simulation`	write	Run a simulation directly with input content.
`run_with_generator`	write	Run a generator script that creates an input file, then execute the solver.
`search_examples`	read	Search for example input files across all backends.
`session_insights`	read	Review knowledge discovered during this session or from saved
`setup_backend`	write	Guided backend setup: detect, plan, install, verify, persist.
`submit_critic_review`	write	Put an independent critic
`transfer_field`	write	Extract field values at an interface from a VTU file and format for transfer.
`validate_input`	read	Validate solver-specific input content before running.
`validate_physics`	read	Validate simulation parameters against physics constraints.
`verify_interface_flux`	read	On a COUPLED task: is your interface flux the right sign, and do
`verify_mesh_independence`	read	Heuristic mesh-independence study for problems WITHOUT an exact
`verify_pde_consistency`	read	Does your field actually satisfy the equation the task stated?
`visualize`	write	Post-process and visualize simulation results.

Trust audit

BLOCKgrade F · trust 39/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	FAIL
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED