A comprehensive Model Context Protocol (MCP) server for solving Constraint Satisfaction Problems (CSP), Linear Programming (LP), Minimax
Gurddy MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. A comprehensive Model Context Protocol (MCP) server for solving Constraint Satisfaction Problems (CSP), Linear Programming (LP), Minimax optimization, and SciPy-powered advanced optimization problems. Built on the gurddy optimization.
Installation goes through your MCP client rather than a global install: point it at gurddy_mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Once Gurddy MCP is connected, these are the calls the assistant has available:
info — Get information about the gurddy package. json { "name": "info", "arguments": {} }run_example — Run a gurddy example. json { "name": "run_example", "arguments": { "example": "n_queens" } } Available examples: lp, csp, n_queens, graph_coloringsolve_n_queens — Solve the N-Queens problem. json { "name": "solve_n_queens", "arguments": { "n": 8 } }solve_sudoku — Solve a 9x9 Sudoku puzzle. json { "name": "solve_sudoku", "arguments": { "puzzle": [[5,3,0,...], [6,0,0,...], ...] } }solve_graph_coloring — Solve graph coloring problem. json { "name": "solve_graph_coloring", "arguments": { "edges": [[0,1], [1,2], [2,0]], "num_vertices": 3, "max_colors"solve_map_coloring — Solve map coloring problem. json { "name": "solve_map_coloring", "arguments": { "regions": ["A", "B", "C"], "adjacencies": [["A", "B"], ["B", "C"]]solve_lp — Solve a Linear Programming (LP) or Mixed Integer Programming (MIP) problem using PuLP. json { "name": "solve_lp", "arguments": { "profits": {solve_production_planning — Solve a production planning optimization problem with optional sensitivity analysis. json { "name": "solve_production_planning", "arguments": {solve_minimax_game — Solve a two-player zero-sum game using minimax (game theory). json { "name": "solve_minimax_game", "arguments": { "payoff_matrix": [ [0, -1, 1], [1solve_minimax_decision — Solve a minimax decision problem under uncertainty (robust optimization). json { "name": "solve_minimax_decision", "arguments": { "scenarios": [solve_24_point_game — Solve the 24-point game with four numbers using arithmetic operations. json { "name": "solve_24_point_game", "arguments": { "numbers": [1, 2, 3, 4] }solve_chicken_rabbit_problem — Solve the classic chicken-rabbit problem with heads and legs constraints. json { "name": "solve_chicken_rabbit_problem", "arguments": {This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Gurddy MCP's toolset — info, run_example, solve_n_queens and 11 more — is a fair guide to whether it matches your workflow. It is maintained by novvoo; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Gurddy MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| info | Get information about the gurddy package. json { "name": "info", "arguments": {} } |
| run_example | Run a gurddy example. json { "name": "run_example", "arguments": { "example": "n_queens" } } Available examples: lp, csp, n_queens, graph_coloring, map_coloring, scheduling, logic_puzzles, optimized_csp, optimized_lp, mi |
| solve_n_queens | Solve the N-Queens problem. json { "name": "solve_n_queens", "arguments": { "n": 8 } } |
| solve_sudoku | Solve a 9x9 Sudoku puzzle. json { "name": "solve_sudoku", "arguments": { "puzzle": [[5,3,0,...], [6,0,0,...], ...] } } |
| solve_graph_coloring | Solve graph coloring problem. json { "name": "solve_graph_coloring", "arguments": { "edges": [[0,1], [1,2], [2,0]], "num_vertices": 3, "max_colors": 3 } } |
| solve_map_coloring | Solve map coloring problem. json { "name": "solve_map_coloring", "arguments": { "regions": ["A", "B", "C"], "adjacencies": [["A", "B"], ["B", "C"]], "max_colors": 2 } } |
| solve_lp | Solve a Linear Programming (LP) or Mixed Integer Programming (MIP) problem using PuLP. json { "name": "solve_lp", "arguments": { "profits": { "ProductA": 30, "ProductB": 40 }, "consumption": { "ProductA": {"Labor": 2, "M |
| solve_production_planning | Solve a production planning optimization problem with optional sensitivity analysis. json { "name": "solve_production_planning", "arguments": { "profits": { "ProductA": 30, "ProductB": 40 }, "consumption": { "ProductA": |
| solve_minimax_game | Solve a two-player zero-sum game using minimax (game theory). json { "name": "solve_minimax_game", "arguments": { "payoff_matrix": [ [0, -1, 1], [1, 0, -1], [-1, 1, 0] ], "player": "row" } } Returns the optimal mixed str |
| solve_minimax_decision | Solve a minimax decision problem under uncertainty (robust optimization). json { "name": "solve_minimax_decision", "arguments": { "scenarios": [ {"A": -0.2, "B": -0.1, "C": 0.05}, {"A": 0.3, "B": 0.2, "C": -0.02}, {"A": |
| solve_24_point_game | Solve the 24-point game with four numbers using arithmetic operations. json { "name": "solve_24_point_game", "arguments": { "numbers": [1, 2, 3, 4] } } Finds arithmetic expressions using +, -, *, / and parentheses to rea |
| solve_chicken_rabbit_problem | Solve the classic chicken-rabbit problem with heads and legs constraints. json { "name": "solve_chicken_rabbit_problem", "arguments": { "total_heads": 35, "total_legs": 94 } } Determines the number of chickens (2 legs) a |
| solve_scipy_portfolio_optimization | Solve nonlinear portfolio optimization using SciPy with quadratic risk models. json { "name": "solve_scipy_portfolio_optimization", "arguments": { "expected_returns": [0.12, 0.18, 0.15], "covariance_matrix": [ [0.04, 0.0 |
| solve_scipy_statistical_fitting | Solve statistical parameter estimation using SciPy with distribution fitting. json { "name": "solve_scipy_statistical_fitting", "arguments": { "data": [1.2, 2.3, 1.8, 2.1, 1.9, 2.4, 1.7, 2.0], "distribution": "normal" } |
{
"mcpServers": {
"gurddy": {
"command": "uvx",
"args": ["gurddy_mcp"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.