MCP.so
登录

MCP ORTools

@MCP-Reasoner

基本信息

分类

其他

许可证

MIT license

传输方式

stdio

作者

MCP-Reasoner

关于 MCP ORTools

Model Context Protocol (MCP) server implementation using Google OR-Tools for constraint solving

#mcp-ortools#constraint-solving#ai-integration

MCP ORTools 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "ortools": {
      "command": "python",
      "args": [
        "-m",
        "mcp_ortools.server"
      ]
    }
  }
}

MCP ORTools 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP-ORTools?

MCP-ORTools is a Model Context Protocol server that integrates Google OR-Tools constraint programming solver with Large Language Models. It enables AI models to submit, validate, and solve constraint satisfaction and optimization problems using JSON-based model specifications.

How to use MCP-ORTools?

Install the package via pip install git+https://github.com/Jacck/mcp-ortools.git, then configure Claude Desktop by adding an ortools MCP server entry pointing to python -m mcp_ortools.server in the MCP configuration file. Submit constraint models in JSON format with variables, constraints, and optional objective sections.

Key features of MCP-ORTools

  • Full OR-Tools CP-SAT solver support
  • JSON-based model specification
  • Integer and boolean variable domains
  • Linear constraints using OR-Tools method syntax
  • Linear optimization objectives with maximize/minimize
  • Support for timeouts and solver parameters

Use cases of MCP-ORTools

  • Solving knapsack problems with variable selection constraints
  • Modeling and optimizing portfolio selection
  • Enforcing binary relationships between decision variables
  • Finding feasible solutions for linear constraint satisfaction problems
  • Setting optimal objective values within given constraints

常见问题

1

What constraint syntax is supported?

Constraints must use OR-Tools method syntax: `.__le__()` for ≤, `.__ge__()` for ≥, `.__eq__()` for equality, `.__ne__()` for not equal. Basic arithmetic (+, -, *) on variables is allowed.

2

What solver statuses can the server return?

The solver returns OPTIMAL, FEASIBLE, INFEASIBLE, or UNKNOWN along with solve time and variable assignments.

3

What are the runtime dependencies?

The server requires Python and the `mcp-ortools` package, which includes Google OR-Tools. No additional runtime or database is needed.

4

How are models validated?

Models are submitted as JSON with required `variables` and `constraints` arrays and an optional `objective` object. The server validates the syntax before solving.

5

What transport or authentication does the server use?

The README configures the server as an MCP server for Claude Desktop via stdio transport. No authentication details are provided.

评论

其他 分类下的更多 MCP 服务器