matlab/mcp-framework-matlab-production-server

Última atividade de origem registrada: 29 de outubro de 2026 às 20:11

Catálogo do SkillsMP atualizado: 9 de novembro de 2026 às 14:22

skills coletadas: 3

Estrelas no GitHub: 36
Forks no GitHub: 11

Instalar com um assistente de IA

Copie este prompt para o assistente de IA que você usa.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/matlab/mcp-framework-matlab-production-server.

README do repositório

Arquivo de origem do README: README.md

Ler o README original

Expandir README completo

# MCP Framework for MATLAB Production Server Publish MATLAB® functions as [Model Context Protocol](https://modelcontextprotocol.io/) tools on [MATLAB Production Server™](https://www.mathworks.com/products/matlab-production-server.html). AI agents call your functions, offering the speed, reliability, and domain-specific performance of MATLAB. ## Prerequisites - [MATLAB](https://www.mathworks.com/products/matlab.html) R2025b or later - [MATLAB Compiler™](https://www.mathworks.com/products/compiler.html), which MATLAB Compiler SDK requires - [MATLAB Compiler SDK™](https://www.mathworks.com/products/matlab-compiler-sdk.html) - [MATLAB Production Server](https://www.mathworks.com/products/matlab-production-server.html) 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](https://modelcontextprotocol.io/clients) (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: ```MATLAB 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. ```MATLAB % 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](./docs/getting-started.md) guide for a complete walkthrough. ## Key Features - **[Building MCP tools](./docs/guides/building-tools.md)** — The framework packages your functions and deploys them to MPS. Supports [single functions](./Examples/Primes/walkthrough.md), [multi-tool servers](./Examples/MultiTool/walkthrough.md), [large data](./Examples/Periodic%20Noise/walkthrough.md), and [structured inputs](./Examples/StructuredData/walkthrough.md). - **[MCP Resources](./docs/guides/resources.md)** — Serve read-only reference data (material properties, calibration tables) alongside your tools, so the LLM uses real values instead of guessing. [Materials example](./Examples/Materials/walkthrough.md) - **[Server metrics](./docs/guides/server-metrics.md)** — Monitor deployed tools with built-in counters at framework, server, and tool level. - **[AI agent skills](./docs/guides/agent-skills.md)** — Let Claude Code build and deploy tools on your behalf from natural language. - **[Discovery](./docs/concepts/discovery.md)** — Deployed tools register with the MPS discovery endpoint so clients can find them automatically. - **[Protocol conformance](./docs/concepts/protocol-conformance.md)** — Servers support MCP 2025-06-18, which uses sessions, and 2026-07-28, which is stateless. The server selects the revision from each request. **Documentation:** [Getting Started](./docs/getting-started.md) | [Cheat Sheet](./docs/cheat-sheet.md) | [Examples](./Examples/) | [Guides](./docs/guides/) | [Concepts](./docs/concepts/) | [Reference](./docs/reference/) | [Release Notes](./ReleaseNotes.md) | [Security](./SECURITY.md) ## License See [license.txt](./license.txt). ## Contact <https://www.mathworks.com/support/contact_us.html> --- Copyright 2025-2026 The MathWorks, Inc. ---

Carregando o README do repositório…

Skills neste repositório

Analistas de garantia de qualidade de software e testadores

1 categorias ocupacionais · 33% classificado

skill

ocupação

descrição

atualizado

mps-mcp-build

sem classificação

Create and deploy MCP tools from MATLAB functions to MATLAB Production Server using the MCP Framework for MATLAB Production Server support package

Idioma do texto original: inglês

2026-10-29

mps-mcp-build

sem classificação

Create and deploy MCP tools from MATLAB functions to MATLAB Production Server using the MCP Framework for MATLAB Production Server support package

Idioma do texto original: inglês

2026-10-29

mps-review

Analistas de garantia de qualidade de software e testadores

Run a code review and publish it to the reviews branch for the review-gate CI check

Idioma do texto original: inglês

2026-08-17

Mostrando 3 de 3 skills coletadas.