Gurddy MCP Server

@novvoo

Basic information

About Gurddy MCP Server

A Model Context Protocol (MCP) server providing solutions for Constraint Satisfaction Problems (CSP) and Linear Programming (LP). Built on the gurddy optimization library, it supports solving a variety of classic problems through two MCP transports: stdio (for IDE integration) an

#csp#lp#optimization

Gurddy MCP Server config

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

{
  "mcpServers": {
    "gurddy": {
      "command": "uvx",
      "args": [
        "gurddy-mcp@latest"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": [
        "run_example",
        "info",
        "install",
        "solve_n_queens",
        "solve_sudoku",
        "solve_graph_coloring",
        "solve_map_coloring",
        "solve_lp",
        "solve_production_planning"
      ]
    }
  }
}

Gurddy MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Gurddy?

Gurddy is an MCP (Model Context Protocol) server that solves Constraint Satisfaction Problems (CSP), Linear Programming (LP), and Minimax optimization problems using the gurddy library. It provides 13 MCP tools over stdio (for IDE integration) and HTTP/SSE transports (for web clients), and is intended for developers and AI assistants needing optimization capabilities.

How to use Gurddy?

Install via pip install gurddy_mcp, then configure the MCP server in your IDE (e.g., Kiro) using a JSON block with command "uvx" and args ["gurddy-mcp@latest"]. Alternatively, run the HTTP server via Docker with docker run -p 8080:8080 gurddy-mcp. Example MCP configuration is provided in the README.

Key features of Gurddy

CSP solving (N‑Queens, Sudoku, graph/map coloring, scheduling)
Linear and Mixed Integer Programming optimization
Minimax and game theory (zero‑sum games, Nash equilibria)
Robust optimization and conservative decision making
Stdio and HTTP/SSE transport support
13 dedicated MCP tools for various problem types

Use cases of Gurddy

Solve classic puzzles like N‑Queens or Sudoku automatically
Optimize production planning under resource constraints
Perform portfolio optimization with risk scenarios
Find optimal strategies in two‑player zero‑sum games
Allocate defender‑attacker resources in security games

Frequently asked questions

What types of problems can Gurddy solve?

Constraint Satisfaction Problems (CSP), Linear Programming (LP) and Mixed Integer Programming (MIP), and Minimax/game theory problems.

What transports does Gurddy support?

Stdio (for local IDE integration) and HTTP/SSE (for remote web clients).

How do I install Gurddy?

Install via `pip install gurddy_mcp`. For HTTP deployment, use the Docker image `gurddy-mcp`.

Is there a live demo available?

Yes, a live demo is hosted at https://gurddy-mcp.fly.dev (indicated by the badge in the README).

Does Gurddy require Python?

Yes, the server is a Python package and requires Python 3.8+ (the badge shows Python support).

Comments

More Developer Tools MCP servers

Kaiva Bridge

Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

ReactVision MCP

ReactVision, Inc

Most MCP servers hand your agent documentation. This one hands it a renderer. Write a single React Native codebase that ships native AR to phones and VR to headsets, then let your agent validate every prop, check each pl

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.