What types of problems can Gurddy solve?
Constraint Satisfaction Problems (CSP), Linear Programming (LP) and Mixed Integer Programming (MIP), and Minimax/game theory problems.
@novvoo
Basic information
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
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"
]
}
}
}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.
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.
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.
Constraint Satisfaction Problems (CSP), Linear Programming (LP) and Mixed Integer Programming (MIP), and Minimax/game theory problems.
Stdio (for local IDE integration) and HTTP/SSE (for remote web clients).
Install via `pip install gurddy_mcp`. For HTTP deployment, use the Docker image `gurddy-mcp`.
Yes, a live demo is hosted at https://gurddy-mcp.fly.dev (indicated by the badge in the README).
Yes, the server is a Python package and requires Python 3.8+ (the badge shows Python support).

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Code review for your coding agent's changes: a cloud bug hunt. #1 on the open ReviewBench. From $4; $0 if clean or minor-only. Works with Claude Code and Codex.

MilliGate is a developer-first remote MCP server that functions as a secure crypto paywall. By leveraging the HTTP 402 (Payment Required) protocol, it allows developers to monetize AI agents, APIs, and digital infrastruc
Comments