optlens MCP server

optlens

A solver-agnostic debugger and explainer for LP and MILP models. Give it a model that is infeasible, or one that solves to an answer you don't trust. optlens finds the conflicting constraints, the smallest changes that fix them, and what each change costs. Every result is text that an agent or a person can read. Use it from your own Python, from Claude Code through the plugin, or from any MCP client.

optlens works on a model that is already built. It does not write models.

<!-- mcp-name: io.github.jjd-lab/optlens -->

Install

Python 3.12 or later:

pip install "optlens[scip,mcp]"   # core: numpy, scipy, HiGHS

To run the quickstart below or the tests, clone the repository and install it from the clone (git clone https://github.com/jjd-lab/optlens && cd optlens && pip install ".[scip,mcp]").

Some networks cannot reach GitHub, for example behind a proxy or a VPN. There, copy the source over another way, such as a zip of the repository. Install it with pip install "[scip,mcp]", and add the Claude Code plugin with claude plugin marketplace add .

Quickstart

import optlens as od
from optlens.session import Session, Version

if __name__ == "__main__":  # solves run in worker processes, which start by re-importing this script
    md = od.load("tests/fixtures/ex_milp_tutorial__rhs_tighten__0.mps")  # LP or MPS
    s = Session({"v0": Version(md, None, "original model")})
    print(s.get_model_overview())   # size, status (here INFEASIBLE), constraint families
    print(s.compute_iis())          # the conflicting constraints, grouped by family
    print(s.fix_menu())             # the smallest change per family that restores feasibility
    print(s.modify_and_resolve(changes=[{"action": "set_rhs", "name": "resource[Monika]", "upper": 1}]))

Save it as a file and run it from the repository root. Keep the if name == "main": guard in any script that solves. Solves run in worker processes. Windows starts them with spawn, and each one re-imports the script. Without the guard, the script runs again in every solver process.

Every Session method returns text, and optlens.session.TOOLS holds the matching JSON schemas for an agent. A session also covers feasibility relaxation, what-if edits as versions, why-not questions, sensitivity and marginal values, suspicious data values, and comparisons between versions or models.

A model built in Pyomo, gurobipy or PuLP loads directly, from the object or from the file that builds it. optlens runs the file without its if name == "main": block and stops at the first solve call (optimize(), solve()). It reads the model of that call. Nothing is solved, so a large gurobipy model loads on Gurobi's size-limited license.

md = od.from_object(model)                      # a Pyomo ConcreteModel, gurobipy Model or PuLP LpProblem
md = od.load("my_model.py")                     # the model it solves, else its one model or build_model()
md = od.load("my_model.py:make_scenario")       # a named model, or a function with no arguments that returns one

LP files written by Gurobi (bracketed names, which HiGHS rejects) load without gurobipy.

Shortened. The full README is on GitHub.