openmdao-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| --host | No | HTTP only. Host to bind; defaults to `127.0.0.1`. | 127.0.0.1 |
| --path | No | HTTP only. Path for the streamable HTTP endpoint. | |
| --port | No | HTTP only. Port to bind. | |
| --workdir | No | Directory for problem specs, recordings and external-code runs. Defaults to `$OPENMDAO_MCP_WORKDIR`, else `~/.openmdao_mcp`. | |
| MPLBACKEND | No | Set to `Agg` for headless deployment, as done by the provided systemd service. | |
| --log-level | No | Log level. Logs always go to stderr. | |
| --transport | No | Transport to use: `stdio` (default) or `streamable-http`. | stdio |
| --allowed-commands | No | Comma-separated executable paths or names that `external_code` components may run, or `*`. Without it, stdio allows any command and streamable-http disables `external_code`. | |
| OPENMDAO_MCP_WORKDIR | No | Environment variable used as the default work directory when `--workdir` is not supplied. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Build, solve, and optimize OpenMDAO problems from declarative specifications. Typical workflow: create_problem (components, nested groups with coupling solvers) -> run_model -> configure_optimization -> check_totals_sweep (detect derivative noise from black-box codes) -> run_doe or run_multistart / run_driver -> query_cases (best feasible design, active constraints, sensitivities) -> export_n2. Every response carries an optional structured 'error'.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pingB | Health check for the OpenMDAO MCP server. |
| create_problemB | Build an OpenMDAO problem from a declarative ProblemSpec (components, nested groups, solvers, design variables, objective, constraints, driver) and persist it as problem_spec.json. |
| update_problemB | Replace a problem's spec and rebuild it. The old problem is kept if the new spec fails to build. |
| load_problemA | Rebuild a persisted problem from its problem_spec.json (for example after a server restart). |
| list_problemsA | List problems that are live in memory or persisted on disk. |
| get_problem_specB | Return the stored ProblemSpec of a problem. |
| close_problemA | Release a problem from memory; with delete_files, also delete its directory and recordings. |
| list_variablesC | List model inputs and/or outputs with units, shape, description and current value. |
| set_inputsB | Set input values, optionally in given units. Values set here are not persisted to the spec. |
| get_outputsB | Read current values of variables, optionally converted to given units. |
| configure_solversA | Set the nonlinear and linear solvers of one group (dotted path, empty for the root), e.g. NonlinearBlockGS or Newton with DirectSolver for a coupled loop. Both slots are overwritten. |
| configure_optimizationA | Set the driver (scipy SLSQP/L-BFGS-B/trust-constr/COBYLA/Nelder-Mead, doe, analysis) and, when given, the design variables, objective and constraints. Gradient-based optimizers need ref/ref0 or scaler on every design variable. |
| run_modelA | Evaluate the model once, optionally after setting inputs. A failed evaluation (AnalysisError) returns success=false instead of an error; converged reports nonlinear-solver convergence. |
| run_driverB | Run the configured driver from the current point. Each run records to its own SqliteRecorder file (see query_cases). Failures are reported with success=false. |
| run_doeB | Design of experiments over the design variables: Latin hypercube (scipy.stats.qmc), full factorial, uniform, or an explicit list, run through DOEDriver. Failed points are reported, not fatal. |
| run_multistartB | Multi-start optimization: LHS sampling, keep the top_k feasible seeds, then a normalized local optimization (SLSQP by default) from each, in spawn worker processes when n_workers > 1. |
| configure_approx_totalsA | Approximate the model's total derivatives by finite differences (forward/central/backward, step, step_calc) or complex step; pass spec=null to remove the approximation. |
| compute_totalsB | Total derivatives of 'of' with respect to 'wrt' at the current point (runs the model first). |
| check_totals_sweepA | Finite-difference total derivatives at several step sizes, flagging derivatives that change with the step (numerical noise from black-box codes) and recommending a step. Run it before SLSQP. |
| query_casesB | Query a case recording with CaseReader: list, history, best_feasible, active_constraints, or sensitivity_ranking. Defaults to the problem's latest recording. |
| export_n2B | Write a standalone N2 diagram (HTML) into the problem directory without opening a browser. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 21 tools
Most tools map to distinct lifecycle stages, and the descriptions clearly separate problem creation, update, loading, and execution. There is minor conceptual overlap between related execution tools such as run_driver, run_doe, and run_multistart, and between list_variables and get_outputs, but their intended uses are still recoverable.
Tool names consistently use lowercase snake_case with an action verb first: get_, create_, update_, load_, list_, configure_, run_, compute_, check_, query_, and export_. The lone single-verb tool, ping, is a standard health-check name and does not meaningfully break the pattern.
At 21 tools the surface is somewhat heavy, but the OpenMDAO workflow legitimately spans problem management, configuration, execution, derivative analysis, case querying, and visualization. Each tool appears to correspond to a meaningful operation rather than duplicating another, though the specialized run and check tools push the count above the typical range.
The tool set covers the full lifecycle: create/update/load/list/close problems, retrieve specs, inspect variables, set inputs, configure solvers/optimization/approximations, run models/drivers/DOE/multistart, compute and verify totals, query recordings, export N2 diagrams, and health-check the server. Deletion is handled through close_problem with delete_files, so there are no obvious dead ends.