neuromechanist/matlab-mcp-tools

A Model Context Protocol (MCP) server that provides tools for developing and running MATLAB files. Integrates with Claude Code, Cursor, and other MCP-compatible clients.
Prerequisites
- Python 3.10+
- MATLAB with Python Engine installed
- uv package manager (required)
Features
1. **Script Execution** - Run complete scripts, individual sections (by index, title, or line range), maintain workspace context between executions, capture plots
2. **Workspace Management** - Get full workspace, retrieve specific variables with field/depth/size control, inspect struct metadata, list and filter variables by name pattern or type
3. **Figure Analysis** - Extract figure metadata (axes, labels, legends), get raw plot data, prepare figures for LLM-based analysis with custom prompts
4. **Code Quality** - Lint MATLAB code via checkcode with severity filtering, supports inline code and file paths
5. **Script Management** - Create scripts, list sections with previews, read script content via MCP resource
Installation
Quick Start (Recommended)
**One-command installation with auto-detection:**
That's it! The installer will:
- ✅ **Auto-detect MATLAB installations** (including external volumes like /Volumes/S1/)
- ✅ **Auto-install UV** package manager if needed
- ✅ **Create optimized virtual environment** with MATLAB-compatible Python version
- ✅ **Install all dependencies** including MATLAB Python engine
- ✅ **Generate MCP configuration** ready for Cursor/Claude Code
- ✅ **Verify installation** works correctly
- ✅ **Optionally configure Cursor** automatically
**Reduces installation time from 15+ minutes to ~2 minutes!**
Advanced Installation
If you need custom configuration:
1. **Clone this repository:**
2. **Set custom MATLAB path** (optional - installer auto-detects):
3. **Run installer:**
Legacy Installation (Manual)
Click to expand legacy manual installation steps
1. Install uv package manager:
2. Set MATLAB path environment variable:
3. Run legacy setup script:
4. Configure Cursor manually:
Testing Installation
Test your installation:
**Installation complete!** The MATLAB MCP server is now ready to use with Cursor/Claude Code.
Usage
1. Start the MCP server:
This is equivalent to running:
You should see a startup message confirming the server is running with 15 tools available.
2. Configure your MCP client. For **Claude Code**, add to .mcp.json:
For **Cursor**, use the auto-generated mcp-pip.json or add to ~/.cursor/mcp.json.
Hint: Find the MATLAB engine path with python -c "import matlab; print(matlab.__file__)".
3. **Available Tools (15):**
| Category | Tool | Description |
|----------|------|-------------|
| Scripts | execute_script | Run MATLAB code or script file |
| | execute_section | Execute by line range |
| | execute_section_by_index | Execute by section index (0-based) |
| | execute_section_by_title | Execute by section title (partial match) |
| | get_script_sections | List sections with titles and previews |
| | create_matlab_script | Create a new .m file |
| Workspace | get_workspace | Get all workspace variables |
| | get_variable | Get specific variable (with field/depth/size control) |
| | get_struct_info | Get struct field metadata without data transfer |
| | list_workspace_variables | List/filter variables by name pattern or type |