Mcp_constrained_optimization

Name: Mcp_constrained_optimization
Author: Sharmarajnish

@Sharmarajnish

Repository

About Mcp_constrained_optimization

No overview available yet

#mcp #constrained-optimization #optimization-server

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "MCP-Constrained-Optimization": {
      "command": "python",
      "args": [
        "examples/nqueens.py"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Mcp_constrained_optimization?

Mcp_constrained_optimization is a general-purpose MCP server for solving combinatorial optimization problems with logical and numerical constraints. It provides a unified interface to multiple optimization solvers, enabling AI assistants to handle complex optimization across various domains.

How to use Mcp_constrained_optimization?

Install via pip install constrained-opt-mcp, then start the server with constrained-opt-mcp. Add it to your MCP client configuration using the command constrained-opt-mcp with no arguments. The server exposes five tools: solve_constraint_satisfaction, solve_convex_optimization, solve_linear_programming, solve_constraint_programming, and solve_portfolio_optimization.

Key features of Mcp_constrained_optimization

Unified interface to Z3, CVXPY, HiGHS, and OR-Tools solvers.
Specialized tools for portfolio optimization and risk management.
Designed for AI assistants via the MCP protocol.
Supports linear, quadratic, convex, and constraint satisfaction problems.
High performance with comprehensive error handling.
Extensible modular architecture for adding new solvers.

Use cases of Mcp_constrained_optimization

Solve constraint satisfaction puzzles like N‑Queens and knapsack problems.
Perform portfolio optimization with Markowitz, Black‑Litterman, or ESG constraints.
Optimize production planning and resource allocation via linear programming.
Schedule workforce, job shop, or nurse shifts with constraint programming.
Manage risk using VaR, CVaR, stress testing, and scenario analysis.

FAQ from Mcp_constrained_optimization

What solvers does Mcp_constrained_optimization support?

It supports Z3 for constraint satisfaction, CVXPY for convex optimization, HiGHS for linear/mixed-integer programming, and OR-Tools for constraint programming.