by matlab
The Simulink Agentic Toolkit gives your AI agent both the tools and the expertise to work effectively with Simulink and Model-Based Design.
# Add to your Claude Code skills
git clone https://github.com/matlab/simulink-agentic-toolkitGive your AI coding agent the ability to read, build, edit, and test Simulink® models using Model-Based Design best practices.
The Simulink Agentic Toolkit packages MathWorks® Model-Based Design expertise for AI coding agents. It connects agents to Simulink through the Model Context Protocol (MCP), giving them both the ability (tools) and the knowledge (skills) to work with Simulink models effectively.
┌───────────┐ ┌───────────┐ ┌──────────┐
│ AI Agent │◄─MCP─►│MCP Server │◄─────►│ MATLAB / │
│ (Claude, │ │ (MATLAB │ │ Simulink │
│ Cursor, │ │ MCP Core) │ └──────────┘
│ Copilot) │ └───────────┘
└───────────┘
▲
│ reads
┌─────┴─────┐
│ Skills │
│ (MBD best │
│ practices)│
└───────────┘
Your agent reads skills for domain knowledge, then calls MCP tools to interact with MATLAB and Simulink. The MATLAB MCP Core Server bridges the connection (downloaded during setup).
No comments yet. Be the first to share your thoughts!
| Platform | Setup | Notes | |----------|-------|-------| | Claude Code | Automated | Also supports no-clone marketplace install (skills only) | | GitHub Copilot | Automated | | | OpenAI Codex | Automated | | | Gemini CLI | Automated | | | Sourcegraph Amp | Automated | | | Cursor | Manual | Untested |
Automated setup has been verified with basic workflows on each platform except Cursor. The toolkit is under active development — please report issues if you encounter problems.
Full walkthrough: See the Getting Started guide for detailed instructions, platform-specific notes, verification steps, and troubleshooting.
Prerequisites:
The Simulink Agentic Toolkit helps you install and configure the MATLAB MCP Core Server, or can be configured to use your existing installation.
Clone the repository, launch your agent from the toolkit directory, and ask it to set up the toolkit.
git clone https://github.com/matlab/simulink-agentic-toolkit.git
cd simulink-agentic-toolkit
Launch your agent (claude, codex, gemini, etc.) and ask:
Set up the Simulink Agentic Toolkit
Setup looks for your MATLAB installation(s), downloads the MCP server, writes your agent's global configuration, and registers skills. Once complete, start a new session in any project directory — Simulink tools and skills are available everywhere.
Claude Code — no clone required: If you already have the MCP server configured, you can add skills directly without cloning:
claude plugin marketplace add "https://github.com/matlab/simulink-agentic-toolkit" claude plugin install model-based-design-core@simulink-agentic-toolkitThis installs skills only. Your existing MCP configuration is not modified. See the Getting Started guide for details.
If you installed the MATLAB MCP Core Server yourself, you just need skills. See Adding Skills Only in the Getting Started guide.
The MCP server connects to a running MATLAB session. Open MATLAB and run:
addpath("/path/to/simulink-agentic-toolkit")
satk_initialize
In MATLAB, open any Simulink model — your own, or a shipped example like f14:
openExample("simulink/AddBlockToModelFromLibraryExample") % only needed for R2023b+
open_system("f14")
Then ask your agent:
Describe the structure of the currently open model.
| Tool | What your agent can do |
|------|------------------------|
| model_overview | Explore model architecture — see subsystem hierarchy, interfaces, and how major components connect |
| model_read | Understand model behavior — inspect blocks, algorithmic expressions, signal flow, and parameter values |
| model_edit | Build and modify models — add blocks, wire signals, create subsystems, and configure parameters |
| model_test | Verify requirements — run human-readable Gherkin tests with automatic harness generation (requires Simulink Test) |
| model_query_params | Inspect any parameter — query block settings, signal properties, solver config, and logging flags |
| model_resolve_params | Get actual values — resolve workspace variables like Kp to their numeric values across all scopes |
Skills are organized in the skills catalog. The core skill group includes:
| Skill | What it teaches your agent |
|-------|---------------------------|
| building-simulink-models | Best practices for structural model changes — adding blocks, wiring, layout |
| filing-bug-reports | Generate standalone bug reports for reproducing, investigating, and fixing issues |
| simulink-agentic-toolkit-setup | MATLAB path configuration, MCP tool initialization, tool selection guidance |
| specifying-mbd-algorithms | Specify algorithms for MBD — system specs, architecture specs, implementation and test plans |
| specifying-plant-models | How to specify plant models for closed-loop simulation |
| testing-simulink-models | How to test model behavior — reproduce issues, verify changes, regression tests |
| generate-requirement-drafts | Requirements generation — prefers Requirements Toolbox (.slreqx) with traceability links when available, falls back to structured YAML |
simulink-agentic-toolkit/
├── .claude-plugin/ # Claude Code + Copilot manifest
├── .cursor-plugin/ # Cursor manifest
├── .agents/plugins/ # Codex marketplace registry
├── .codex-plugin/ # Codex plugin definition
├── gemini-extension.json # Gemini CLI MCP config
├── skills-catalog/ # Agent skills (not auto-discovered)
│ ├── model-based-design-core/ # Core MBD skills (6 skills)
│ └── PRODUCT-GROUP-NAME/ # Placeholder for additional skill groups
├── tools/ # MCP tool implementations
├── satk_initialize.m # MATLAB setup entry point
└── research-previews/ # Curated example tasks
The Agentic Task Explorer provides curated, multi-step tasks that demonstrate what agents can do with Simulink — model understanding, creation, modification, testing, bug fixing, and verification. Each task includes Simulink models and supporting files, ready to go.
slAgenticTaskExplorer
Select a task from the interactive UI. The explorer stages it into an isolated workspace with all required files, then opens your coding agent. Each task presents step-by-step prompts — copy each prompt into your coding agent and watch it work.
This is a research preview. Behavior and interfaces may change.
model_testThis toolkit relies on strong multi-step reasoning, tool use, and coding performance from the AI model.
We have tested the toolkit with higher-capability models, including Claude Opus and Sonnet, OpenAI GPT-5 models, and Gemini Pro models, and have generally seen good results on demanding workflows.
Model capability has a significant impact on quality. In our testing, lightweight or lower-capability models were less reliable for tasks such as model construction and complex edits, and were more likely to produce incomplete or incorrect results. These models may still be sufficient for simpler tasks, but for the best overall experience we recommend using a higher-capability model.
| Resource | Description | |----------|-------------| | Getting Started | Setup tutorial with per-agent instructions and troubleshooting | | Skills Catalog | Browse all agent skill groups and individual skills |
MATLAB and Simulink are registered trademarks of The MathWorks, Inc. See mathworks.com/trademarks for a list of additional trademarks. Other product or brand names may be trademarks or registered trademarks of their respective holders.
If you encounter a bug, use the filing-bug-reports skill to generate a report before opening a GitHub issue. Ask your agent:
File a bug report for this issue
The skill au