MCP-ORTools logo

MCP-ORTools

by Jacck

MCP-ORTools is a server implementation using Google OR-Tools for constraint solving. It's designed for use with Large Language Models through standardized constraint model specification.

View on GitHub

Last updated: N/A

What is MCP-ORTools?

MCP-ORTools integrates Google's OR-Tools constraint programming solver with Large Language Models through the Model Context Protocol, enabling AI models to submit, validate, and solve constraint satisfaction and optimization problems.

How to use MCP-ORTools?

Models are specified in JSON format, defining variables, constraints (using OR-Tools method syntax), and an optional optimization objective. The server can be installed via pip and configured with Claude Desktop. Solutions are returned in JSON format.

Key features of MCP-ORTools

  • Full OR-Tools CP-SAT solver support

  • JSON-based model specification

  • Support for integer and boolean variables

  • Support for linear constraints and optimization objectives

Use cases of MCP-ORTools

  • Portfolio selection problems

  • Knapsack problems

  • General constraint satisfaction problems

  • Optimization problems

FAQ from MCP-ORTools

What is the Model Context Protocol (MCP)?

MCP is a standardized protocol for interacting with constraint solvers from Large Language Models.

What constraint syntax is supported?

Constraints must use OR-Tools method syntax, such as .le() for less than or equal.

What variable types are supported?

The server supports integer and boolean variables.

How are solutions returned?

Solutions are returned in JSON format, including the status, solve time, variable values, and objective value.

What status values are possible?

Possible status values include OPTIMAL, FEASIBLE, INFEASIBLE, and UNKNOWN.