MCP-ORTools
@Jacck
Model Context Protocol (MCP) server implementation using Google OR-Tools for constraint solving
Overview
What is MCP-ORTools?
A Model Context Protocol (MCP) server implementation using Google OR-Tools for constraint solving. Designed for use with Large Language Models through standardized constraint model specification.
How to use MCP-ORTools?
Install the package via pip install git+https://github.com/Jacck/mcp-ortools.git, then configure it as an MCP server in Claude Desktop by adding the server entry to claude_desktop_config.json with command python -m mcp_ortools.server. Models are submitted in JSON format with variables, constraints, and an optional objective.
Key features of MCP-ORTools
- Integrates Google OR-Tools CP-SAT solver
- JSON-based model specification
- Supports integer and boolean variables
- Linear constraints using OR-Tools method syntax
- Linear optimization objectives and solver parameters
Use cases of MCP-ORTools
- Solving knapsack and portfolio selection problems
- Optimizing linear objectives with constraints
- Enabling AI models to solve constraint satisfaction problems
- Modeling binary logic and variable relationships
FAQ from MCP-ORTools
What solver does MCP-ORTools use?
It uses Google OR-Tools CP‑SAT solver for constraint satisfaction and optimization.
How are models specified?
Models are specified in JSON with three sections: variables (name and domain), constraints (OR‑Tools method syntax), and an optional objective (linear expression and maximize/minimize flag).
What status values can the solver return?
The solver returns OPTIMAL, FEASIBLE, INFEASIBLE, or UNKNOWN.
What operations are supported in constraints?
Basic arithmetic (+, -, *) and comparisons via .__le__(), .__ge__(), .__eq__(), .__ne__().
What is the license?
MIT License.
