
MATLAB Agentic Toolkit
PluginMathWorks 官方工具包:通过 MATLAB 安装器配置 MCP 服务器,让 agent 运行代码、跑测试、做静态检查;信号处理、控制、统计与机器学习等领域技能组可作为 Claude Code 插件安装。需要 MATLAB R2021a 及以上。
MATLAB Agentic Toolkit
English • Español • 日本語 • 한국어 • 简体中文
The MATLAB® Agentic Toolkit allows you to use AI agents with MATLAB by giving your AI agent the knowledge and context to work efficiently with MATLAB and its toolboxes. Use this toolkit to provide proven MATLAB capabilities to your agent. This toolkit can prevent your AI coding agent from hallucinating toolbox functions, missing new features, and wasting time with extra steps that experienced MATLAB users would skip.
Use this toolkit to:
-
Connect your AI agent to MATLAB. This toolkit does this by automatically installing the MATLAB MCP Server. You can then use your agent to write idiomatic code, generate and run tests, diagnose errors, build apps, and more.
-
Provide curated expertise, called skills, to your agent. These skills equip your agent with knowledge of MATLAB workflows, conventions, and best practices while minimizing token burn.
[!Note] To use AI agents efficiently with Simulink®, install Simulink Agentic Toolkit. When you install either toolkit, you can choose to install both toolkits.
Requirements
- MATLAB R2021a or later
- AI coding agent that supports MCP servers and skills. Supported agents are configured automatically. Otherwise, refer to your agent’s documentation to manually configure the MCP server and install skills. Supported agents include:
- Claude Code
- GitHub® Copilot
- OpenAI® Codex
- Gemini™ CLI
- Amp
Get Started with MATLAB Agentic Toolkit
These steps show you how to use the MATLAB Agentic Toolkit to install the MATLAB MCP Server and add skills to your agent.
Note: For instructions on installation from local files, installation in an offline environment, configuration options for this toolkit, platform-specific notes, verification steps, troubleshooting, and manual setup without the installer, see Configuration and Troubleshooting. If you already have the MCP server installed and only need to add skills, see Adding Skills Only.
Install MATLAB Agentic Toolkit from MATLAB
Follow these steps to set up the MATLAB Agentic Toolkit in MATLAB.
- To download the agentic toolkit installer package, click agenticToolkitInstaller.mltbx.
- Open the downloaded file with MATLAB to install the installer add-on.
- In MATLAB, run this command.
setupAgenticToolkit("install")
- Install only the skill groups relevant to your work. This helps your agent reliably trigger the right skills. To add more skill groups later, re-run the installer.
- By default, your agent creates a new MATLAB session when you call it. To connect your agent to the existing MATLAB session, run this command in the MATLAB command window.
shareMATLABSession()
If you are running multiple MATLAB sessions, the agent connects to the MATLAB session where you most recently ran this command.
Alternatively, you can also add this command to your MATLAB Startup Script.
Install MATLAB Agentic Toolkit from Command Line
If you are using Claude Code or OpenAI Codex, you can also set up the MATLAB Agentic Toolkit, Simulink Agentic Toolkit, and MATLAB MCP Server together on an operating system command line using the Agentic Toolkit Installer. For details, see Agentic Toolkit Installer.
Verify
Ask your agent:
What version of MATLAB is running? List the installed toolboxes.
Run and Test MATLAB Code Using MCP Tools
After you install the MATLAB Agentic Toolkit, your agent can use these tools provided by the MATLAB MCP Server.
| Tasks you can ask your agent to do | Tool used by agent |
|---|---|
| Run MATLAB code and return command window output | evaluate_matlab_code |
| Run a MATLAB program | run_matlab_file |
Run tests via runtests with structured results | run_matlab_test_file |
| Static analysis with the Code Analyzer | check_matlab_code |
| List installed MATLAB version and toolboxes | detect_matlab_toolboxes |
The server also provides two MCP resources: matlab_coding_guidelines (coding standards) and plain_text_live_code_guidelines (Live Script format rules). These resources provide reference information that agents can read as needed.
Run MATLAB Workflows Using Agent Skills
After you install the MATLAB Agentic Toolkit, your agent can use MathWorks® curated skills. For best results, install only the skill groups relevant to your work — agents are more reliable at triggering skills when fewer are loaded. You can also manually trigger a specific skill by name (e.g., /matlab-write-tests in Claude Code) to guarantee it loads. To read details about all the skills, see the skills catalog. Skill groups include:
MATLAB Skills
| Skill Group | Description |
|---|---|
| MATLAB Core | Create, debug, review, and manage MATLAB code and installations |
| MATLAB App Building | Build MATLAB apps programmatically using UI components, layouts, callbacks, and web integration |
| MATLAB Data Import and Analysis | Import, export, and analyze data in MATLAB using tables, timetables, filtering, aggregation, and time-series operations |
| MATLAB External Language Interfaces | Call Python® libraries from MATLAB and upgrade MEX files to the interleaved complex API |
| MATLAB Programming | Write robust MATLAB functions with validated inputs |
| MATLAB Software Development | Write and run tests, modernize legacy code, optimize performance and memory, document and create toolboxes, create projects, manage packages, and develop build plans |
Toolbox Skills
| Skill Group | Supported Products |
|---|---|
| Aerospace | Aerospace Toolbox™ |
| AI and Statistics | Curve Fitting Toolbox™, Deep Learning Toolbox™, Embedded Coder™, Fixed-Point Designer™, MATLAB Coder™, MATLAB Compiler SDK™, MATLAB Report Generator™, Optimization Toolbox™, Parallel Computing Toolbox™, Statistics and Machine Learning Toolbox™, Deep Learning Toolbox Converter for ONNX Model Format™, Deep Learning Toolbox Converter for PyTorch Models™, and Deep Learning Toolbox Converter for TensorFlow Models™ |
| Automotive | Automated Driving Toolbox™, Computer Vision Toolbox™, RoadRunner, RoadRunner Scenario, RoadRunner Scene Builder, Sensor Fusion and Tracking Toolbox™, Automated Driving Toolbox Interface for Eclipse SUMO Traffic Simulator™, and Scenario Builder for Automated Driving Toolbox™ |
| Cloud Solutions | MATLAB Drive™ |
| Code Generation | Embedded Coder, Fixed-Point Designer, GPU Coder™, MATLAB Coder, MATLAB Test™, Parallel Computing Toolbox, and MATLAB Coder Support Package for PyTorch and LiteRT Models™ |
| Computational Biology | SimBiology™ and Statistics and Machine Learning Toolbox |
| Computational Finance | Datafeed Toolbox™, Financial Instruments Toolbox™, Financial Toolbox™, and Spreadsheet Link™ |
| Control Systems | Control System Toolbox™, Predictive Maintenance Toolbox™, Signal Processing Toolbox™, Statistics and Machine Learning Toolbox, and System Identification Toolbox™ |
| Image Processing and Computer Vision | Computer Vision Toolbox, Deep Learning Toolbox, Image Processing Toolbox™, Lidar Toolbox™, Medical Imaging Toolbox™, Optical Design and Simulation Library for Image Processing Toolbox™, and Visual Inspection Toolbox™ |
| Math and Optimization | Optimization Toolbox, Partial Differential Equation Toolbox™, and Symbolic Math Toolbox™ |
| Parallel Computing | Parallel Computing Toolbox and MATLAB Parallel Server™ |
| Radar | Mapping Toolbox™, Phased Array System Toolbox™, Radar Toolbox™, Sensor Fusion and Tracking Toolbox, and Signal Processing Toolbox |
| Reporting and Database Access | Database Toolbox™, MATLAB Report Generator, Parallel Computing Toolbox, and Simulink Report Generator™ |
| RF and Mixed Signal | Antenna Toolbox™, Mixed-Signal Blockset™, RF Blockset™, RF PCB Toolbox™, RF Toolbox™, SerDes Toolbox™, Signal Integrity Toolbox, Signal Processing Toolbox, and Statistics and Machine Learning Toolbox |
| Robotics and Autonomous Systems | Navigation Toolbox™, UAV Toolbox™, and Robotics System Toolbox™ |
| Signal Processing | Audio Toolbox™, DSP HDL Toolbox™, DSP System Toolbox™, Fixed-Point Designer, HDL Coder™, Signal Processing Toolbox, and Wavelet Toolbox™ |
| Test and Measurement | Data Acquisition Toolbox™, Image Acquisition Toolbox™, Image Processing Toolbox, Industrial Communication Toolbox™, Vehicle Network Toolbox™, and MATLAB Support Package for Arduino Hardware™ |
| Wireless Communications | 5G Toolbox™, Bluetooth® Toolbox™, Communications Toolbox™, Satellite Communications Toolbox™, Wireless Network Toolbox™, Wireless Testbench™, WLAN Toolbox™, and Wireless Testbench Support Package for NI USRP Radios™ |
Update MATLAB Agentic Toolkit
To update the toolkit, download the latest installer add-on by clicking agenticToolkitInstaller.mltbx. Open the downloaded file with MATLAB, and run this command in MATLAB.
setupAgenticToolkit("update")
This updates the skills, configurations, and MCP server binary for both the MATLAB and Simulink Agentic Toolkits.
Security Considerations
When using the MATLAB Agentic Toolkit and MATLAB MCP Server, you should thoroughly review and validate all tool calls before you run them. Always keep a human in the loop for important actions and only proceed once you are confident the call will do exactly what you expect. For more information, see User Interaction Model (MCP) and Security Considerations (MCP).
Data Collection
The MATLAB MCP Server collects anonymized usage data by default. For full details, see Data Collection in the MCP server documentation. To opt out, see Disable Data Collection.
Licensing and Usage
The license is available in the LICENSE.md file in this GitHub repository.
MCP servers are only permitted to be used with MATLAB in accordance with the MathWorks Software License Agreement, and must not be shared by multiple users. Contact MathWorks if you need to support shared or centralized server use.
Support and Contributions
MathWorks encourages you to use this repository and provide feedback. Pull requests are not enabled on this repository. To request technical support or submit an enhancement request, create a GitHub issue or contact technical support.
Copyright 2026 The MathWorks, Inc.
相关资源

MATLAB MCP Server
MCPMathWorks 官方出品,让 agent 启动本机 MATLAB,编写并运行脚本和单元测试、检查代码风格与潜在错误,适合用 MATLAB 做数值计算、仿真和数据分析的工程师、科研人员与学生。需本机安装已授权的 MATLAB R2021a 以上,并下载服务器程序。
matlab/matlab-mcp-server1.7k
Simulink Agentic Toolkit
PluginMathWorks 官方工具包:通过 MATLAB MCP 服务器让 agent 读取、搭建、修改和测试 Simulink 模型,附带控制系统、Simscape 物理建模、代码生成与合规检查等技能,支持 Claude Code、Codex 等。需要已授权的 MATLAB R2023a 及以上与 Simulink,先在 MATLAB 中运行官方安装器。
matlab/simulink-agentic-toolkit1.2k
Math Modeling Skills
Skill国赛 CUMCM 与美赛 MCM/ICM 备赛两件套:solver 拆题、按 95+ 场景决策矩阵选模型并给出 Python/MATLAB 代码模板;paper 按获奖论文规律指导摘要、模型检验与排版自查。适合备赛学生和指导老师,运行代码需本地 Python 或 MATLAB。
Lupynow/math-modeling-skills423
Scientific Agent Skills
SkillK-Dense 维护的 166 个科研技能合集(原 Claude Scientific Skills):覆盖生物信息、化学信息、临床研究、材料与物理等领域,含统一查询 PubChem、UniProt 等 78 个公共数据库的技能。
K-Dense-AI/scientific-agent-skills51.2k
Jupyter Notebooks
Skill创建、修改与校验可复现的 Python / SQL Jupyter Notebook:按分析报告或教程结构组织单元格,结论对照实际输出,交付前从头到尾执行一遍。OpenAI 官方维护,属于 openai/plugins 的 Data Analytics 插件。
openai/plugins7.5k
Jupyter MCP Server
MCP让 agent 实时连接 Jupyter Notebook:读写、插入与执行单元格,并读取图表等多模态输出,适合交互式数据分析。需自备 JupyterLab 或 JupyterHub,Datalayer 开源维护。
datalayer/jupyter-mcp-server1.3k