Optimization Solver (LP / MIP Scheduling)
Server Details
Solve production, blending, transport and scheduling problems with LP and MIP.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- Saify-Technologies/saifs-ai-mcps-docs
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools have distinct roles: optimization_solver solves models directly, while optimization_solver_get_engine generates a standalone Python script for large models or sandbox use. The ~3,000 variable threshold is clearly stated, though both still concern optimization solving, so selection requires attention to size/context.
Both names share the optimization_solver prefix, but the first is a noun-like tool name while the second adds a verb phrase (get_engine). This is readable but not a consistent verb_noun pattern across the set.
Two tools is thin for a solver server, though the second exists specifically to cover scale and sandbox scenarios. Each earns its place, but the overall surface is borderline minimal.
The main tool covers multiple problem templates, sensitivity analysis, infeasibility diagnostics, and current-plan comparison, while the second handles large models and MPS files. There is little explicit support for auxiliary lifecycle operations such as saving or listing problem instances, but core solving needs are covered.
Available Tools
2 toolsoptimization_solverOptimization Solver (LP / MIP, scheduling, allocation)ARead-onlyInspect
Find the best plan within limits and explain it. Templates (problem_type): production_mix (products with profit, min/max and use of each resource + resources with available amounts); blend (ingredients with cost and nutrient columns + requirements with min/max, batch_size); transportation (sources with supply, destinations with demand, costs per route); schedule (periods with staff required + shifts or shift_length; or staff + shifts for a roster; or jobs + machines); allocation (projects with value and cost + budget, groups, dependencies); custom (objective + constraints as text such as '3x + 2y <= 18', or MPS). Returns the optimal plan, decision cards, shadow prices with valid ranges (value of one more unit of each limit), reduced costs and price ranges, proven bounds for whole-number plans, conflicting limits with the smallest fix when no plan exists, and the gain over a current_plan. Uses simplex, branch and bound (MIP) and the transportation simplex. Not for forecasting demand, nonlinear or stochastic models, or vehicle routing with time windows. Up to ~3,000 variables; larger: optimization_solver_get_engine.
Inputs: mps, jobs, basis, costs, +36 more. Returns: plan, alerts, status, message, +7 more
optimization_solver_get_engineOptimization Solver — Get Engine Script (large models)ARead-onlyInspect
For models above ~3,000 variables or constraints, long runs (time limit over 60 s), MPS files, or any table already in your code sandbox. Returns a complete numpy-only Python script with the same engine as optimization_solver; it reads the tables (CSV / TSV / JSON) or MPS file named in the call, prints the decision cards and the plan summary, and writes the full result to optimization_result.json. No data reaches this server on this path.
Inputs: params, mps_path, jobs_path, costs_path, +17 more. Returns: notes, paths, script, language, +7 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Optimize crew and workforce schedules, resource allocation, and routing with linear and mixed-inte…
Solve linear, quadratic and mixed-integer optimisation models; get each variable's value by name.
31Builds optimal 24/7 staff rosters with a real MILP solver: rest rules, skills, nights, fairness.
Solve LP, MILP, QP and convex models with checked answers: feasibility, duals, KKT proofs.
1
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables solving linear programming (LP) and mixed-integer linear programming (MILP) optimization problems through natural language, with built-in simplex and branch-and-cut solvers plus infeasibility diagnostics. Includes optional OR-Tools fallback for larger problems and supports parsing optimization problems from natural language descriptions.MIT
- AlicenseBqualityDmaintenanceMathematical Optimization MCP Server with PuLP and OR-Tools support135MIT
- AlicenseNot gradedqualityDmaintenanceProvides linear programming (LP), mixed-integer programming (MIP), and quadratic programming (QP) optimization capabilities using the HiGHS solver, enabling AI assistants to solve complex optimization problems like production planning, logistics, and portfolio optimization.58 npm17MIT
- AlicenseAqualityDmaintenanceEnables solving complex combinatorial optimization problems with logical and numerical constraints through multiple solvers (Z3, CVXPY, HiGHS, OR-Tools). Specializes in portfolio optimization, scheduling, resource allocation, and constraint satisfaction problems.55Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.