Constrained Optimization

General Purpose MCP Server (AI Agent) for Constrained Optimization

python

3

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "sharmarajnish-mcp-constrained-optimization": {
      "command": "constrained-opt-mcp",
      "args": []
    }
  }
}

You can solve a wide range of optimization and constraint problems by running a single MCP server that interfaces with multiple solvers. This server lets you define problems with logical constraints, convex objectives, and portfolio optimization, then solve them through a consistent API from your AI assistant or client.

How to use

Connect to the MCP server from your client by starting the local server process and registering its command with your MCP client configuration. You will run the server locally and then point your client at the local endpoint using the provided MCP entry.

How to install

# Install the package
pip install constrained-opt-mcp

# Or install from source
git clone https://github.com/your-org/constrained-opt-mcp
cd constrained-opt-mcp
pip install -e .

Additional sections

Start the MCP server locally and connect from your client. The server is invoked via the constrained-opt-mcp CLI and exposes a standard set of tooling to solve constraint satisfaction, convex optimization, linear programming, constraint programming, and portfolio optimization.

Example usage from your client configuration shows a simple local stdio setup that points to the CLI you installed. The server supports multiple problem types through dedicated tools.

Examples illustrate common problem domains you can solve.

Examples

Constraint Satisfaction Problem and Portfolio, Linear Programming, and other combinatorial optimization demos are provided to illustrate how to formulate problems and interpret results.

Notes

Environment and language details reflect a Python-based MCP server setup. If you need to integrate this with an AI assistant, ensure your client registers the server and knows how to invoke each solver tool.

Available tools

solve_constraint_satisfaction

Solve logical constraint problems using the constraint solver interfaces.

solve_convex_optimization

Solve convex optimization problems leveraging convex solvers.

solve_linear_programming

Solve linear programming problems with standard linear constraints.

solve_constraint_programming

Solve constraint programming problems with a discrete domain approach.

solve_portfolio_optimization

Solve portfolio optimization problems including returns and risk considerations.