drio
Open app

MCP Solver

Source

Model Context Protocol (MCP) server for constraint optimization and solving"

Catalog onlyCatalog onlySTDIO

Overview

MCP Solver is a server that implements the Model Context Protocol (MCP) to enable Large Language Models (LLMs) to solve constraint satisfaction problems using MiniZinc constraint programming.

To use MCP Solver, install the package via pip from GitHub. Once installed, you can interact with the server to submit constraint models, validate them, and retrieve solutions using provided tools.

  • Comprehensive support for MiniZinc constraint models. - Asynchronous solving capabilities with timeout management. - Validation of parameters and type checking for robustness. - Management of the solution state and automatic inclusion of libraries based on constraints. - Monitoring of the solver's progress and state.
  1. Solving complex theatrical casting problems based on various constraints.
  2. Assisting in resource allocation decisions in various fields.
  3. Supporting optimization tasks in AI-driven applications.

Add to your AI client

Use these steps to connect MCP Solver in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-solver-szeider": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-solver-szeider"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-solver-szeider": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-solver-szeider"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-solver-szeider": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-solver-szeider"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-solver-szeider": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-solver-szeider"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-solver-szeider": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-solver-szeider"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-solver-szeider": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-solver-szeider"
      ]
    }
  }
}

FAQ

What programming languages does MCP Solver support?

MCP Solver is built to be used with Python (version 3.9+). You will also need MiniZinc with the Chuffed solver installed.

Is MCP Solver suitable for production use?

MCP Solver is in its prototype stage and should be used with caution, primarily for experimentation.

Where can I find more examples?

Further sample chat dialogs and examples are included in the repository's 'examples' folder.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":429,"uuid":"2d869827-bfa8-435d-9013-882dc88e1494","name":"mcp-solver","title":"MCP Solver","description":"Model Context Protocol (MCP) server for constraint optimization and solving\"","avatar_url":"https://avatars.githubusercontent.com/u/16817638?v=4","created_at":"2024-12-16T07:23:46.000Z","updated_at":"2024-12-19T12:38:38.250Z","status":"created","author_name":"szeider","author_avatar_url":"https://avatars.githubusercontent.com/u/16817638?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/szeider/mcp-solver","target":"_self","content":"$29","summary":"$2a","img_url":"https://camo.githubusercontent.com/3787e8c957bf8dd7a39c864bbe2d66870c177b148d529437554517985a5ff41a/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4d43502d436f6d70617469626c652d677265656e2e737667","type":null,"metadata":"{\"star\":\"80\",\"license\":\"MIT license\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-05-13 11:13:40\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data