Mrugankpednekar Mcp Optimizer

Built on top of CrewAI and SciPy's HiGHS solver, this server wraps linear and mixed-integer program solvers behind five MCP tools: solve_linear_program, solve_mixed_integer_program, parse_natural_language, diagnose_infeasibility, and solve_word_problem_with_data. The last one reads CSV, JSON, or Excel files and automatically extracts values to feed into optimization models. You supply LP models as JSON structures with variables, constraints, and objective terms, or describe problems in plain English and let the parser convert them. The MILP solver uses lightweight branch-and-bound or falls back to OR-Tools. Reach for this when you need to schedule shifts, allocate resources, or solve routing problems directly from Claude without coding up optimization logic yourself.