将MATLAB®函数作为模型上下文协议工具发布在MATLAB生产服务器™上。AI代理调用你的函数，提供MATLAB的速度、可靠性和领域特定性能。

先修条件

• MATLAB R2025b 或更高版本
• MATLAB 编译器 SDK™
• MATLAB 生产服务器 R2022a 或更高版本
• MCP 客户端（Claude Desktop、Claude Code、带 Copilot 的 VS Code，或任何支持 HTTP 的客户端）

安装

在MATLAB中，打开插件资源管理器（主页→插件标签），搜索“MCP Framework for MATLAB Production Server”。选择安装。

如果你使用AI编码代理，注册构建技能，这样代理可以代你构建和部署工具：

快速启动

要将函数作为MCP工具部署到运行在localhost:9910上的MATLAB生产服务器实例中，请运行以下MATLAB代码。

你的功能现在对连接到该服务器的任何MCP客户端开放。完整攻略请参见入门指南。

主要特色

• 构建MCP工具 — 该框架将你的函数打包并部署到MPS。支持单函数、多工具服务器、大数据和结构化输入。

MCP Framework for MATLAB Production Server

Publish MATLAB® functions as Model Context Protocol tools on MATLAB Production Server™. AI agents call your functions, offering the speed, reliability, and domain-specific performance of MATLAB.

Prerequisites

• MATLAB R2025b or later
• MATLAB Compiler™, which MATLAB Compiler SDK requires
• MATLAB Compiler SDK™
• MATLAB Production Server R2025b or later. Archives built in R2025b need the R2025b MATLAB Runtime, and a server can host runtimes from its own release or earlier.
• An MCP client (Claude Desktop, Claude Code, VS Code with Copilot, or any HTTP-capable client)

Install

In MATLAB, open the Add-On Explorer (Home tab → Add-Ons) and search for “MCP Framework for MATLAB Production Server.” Select Install.

If you use an AI coding agent, register the build skill so the agent can build and deploy tools on your behalf:

prodserver.mcp.agent.setup

Quick Start

To deploy a function as an MCP tool to an instance of MATLAB Production Server running on localhost:9910, run the following MATLAB code.

% Build an MCP tool from a function — the framework runs your example to determine parameter types
ctf = prodserver.mcp.build("principalStress", ...
    example=@() principalStress([120 -50 80], "max"), ...
    server="http://localhost:9910");

% Verify deployment
prodserver.mcp.ping("http://localhost:9910/principalStress/mcp")

% Call the tool directly
prodserver.mcp.call("http://localhost:9910/principalStress/mcp", ...
    "principalStress", [120 -50 80], "maxShear")

Your function is now available to any MCP client connected to that server. See the Getting Started guide for a complete walkthrough.

Key Features

• Building MCP tools — The framework packages your functions and deploys them to MPS. Supports single functions, multi-tool servers, large data, and structured inputs.
• MCP Resources — Serve read-only reference data (material properties, calibration tables) alongside your tools, so the LLM uses real values instead of guessing. Materials example
• Server metrics — Monitor deployed tools with built-in counters at framework, server, and tool level.