matlab/matlab-agentic-toolkit

The MATLAB Agentic Toolkit brings trusted MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.

What it solves

This toolkit prevents AI coding agents from hallucinating MATLAB toolbox functions, missing new features, and taking inefficient paths that experienced MATLAB users would avoid. It provides AI agents with the necessary context, trusted capabilities, and curated expertise to work effectively within the MATLAB environment.

How it works

The toolkit operates through two primary mechanisms:

  1. MATLAB MCP Server: It automatically installs a Model Context Protocol (MCP) server that allows agents to interact directly with MATLAB. This enables tools for running MATLAB code, executing programs, running tests with structured results, performing static analysis via the Code Analyzer, and detecting installed toolboxes.
  2. Curated Skills: It provides "skills"—sets of knowledge and best practices—that equip agents with expertise in specific MATLAB workflows (e.g., App Building, Data Analysis, Software Development) and various specialized toolboxes (e.g., AI and Statistics, Robotics, Signal Processing).

Who it’s for

Developers and engineers using AI coding agents (such as Claude Code, GitHub Copilot, OpenAI Codex, Gemini CLI, or Amp) who want to integrate these agents with MATLAB R2021a or later.

Highlights

  • Direct MATLAB Integration: Connects agents to active MATLAB sessions using the shareMATLABSession() command.
  • Extensive Skill Library: Offers curated expertise across a wide range of domains including Aerospace, Automotive, Control Systems, and Wireless Communications.
  • MCP Toolset: Provides specific tools for code evaluation, file execution, and toolbox detection.
  • Coded Guidelines: Includes reference resources for MATLAB coding standards and Live Script format rules.

Related

  • Project
    matlab/matlab-mcp-server

    MATLAB MCP Server is a Go‑based service that lets AI assistants (Claude, Copilot, Codex, etc.) start MATLAB, run scripts, perform static code checks, and query toolbox info via the Model Context Protocol. It ships pre‑built binaries for all major OSes, supports custom tool extensions, and can attach to existing MATLAB sessions. Intended for developers who want to embed real MATLAB computation inside LLM‑driven workflows, it requires a valid MathWorks license and offers configurable startup options, logging, and optional telemetry.

  • Project
    matlab/simulink-agentic-toolkit

    The Simulink Agentic Toolkit lets LLM coding agents (Claude, Copilot, Codex, Gemini, etc.) interact with Simulink models through a MATLAB MCP Server. It provides ready‑made tools (e.g., model_overview, model_edit) and a catalog of skills that encode Model‑Based Design best practices. An automated installer sets up the MCP server, registers the tools, and adds the skills to the chosen agent. After a one‑time `satk_initialize` in MATLAB, the agent can read, edit, test, and validate Simulink models safely, with optional support for custom block libraries.

  • Project
    aws/agent-toolkit-for-aws

    A toolkit that provides AI coding agents with the tools, knowledge, and guardrails needed to build, deploy, and manage applications on AWS.

  • Project
    dbt-labs/dbt-mcp

    An MCP server that provides AI agents with tools to interact with dbt Core, Fusion, and Platform, enabling them to query data, manage lineage, and execute dbt workflows.

  • Project
    mondaycom/mcp

    An open framework and MCP server that enables AI agents to securely interact with monday.com to manage projects, track tasks, and execute workflows.