From the rules to a checked solution
Constraint programming (CP) is used in practice for production scheduling, shift rostering, timetabling, routing, and cutting and packing, among many other applications. It is also used to solve a wide range of combinatorial problems in academic research. OpenConstraint currently provides worked case studies and an open-source Model Context Protocol (MCP) server that runs on your machine.
Worked constraint problems
Commercial printing
Online print shop schedulingAssign machines and start times to each operation.
Healthcare
Skilled nurse rosteringStaff shifts under skill, rest, and contract rules.
Manufacturing
Two-dimensional guillotine cuttingChoose rectangular pieces and plan edge-to-edge cuts on one sheet.
Manufacturing
Assembly line balancingAssign tasks to stations, using as few as possible.
A local-first MCP server
Use the open-source openconstraint-mcp server with an MCP client such as Claude Code or Codex to develop, check, and solve constraint models with MiniZinc and OR-Tools CP-SAT. It runs on your machine and collects no telemetry.
- The client's language model proposes a constraint model.
- The server validates the model and its data, then runs it.
- The solver searches for a solution.
- A separate checker, when you supply one, verifies the result.
Have a constraint problem?
Describe the decisions to make, the rules a valid solution must satisfy, and any objective you want to optimize. Questions about modeling, the case studies, and OpenConstraint are welcome. The issue tracker is public, so leave out confidential and personal data.