MATLAB
Execute MATLAB scripts and functions via MCP clients. Requires a local MATLAB installation.
MATLAB MCP Server
This Model Context Protocol (MCP) server provides integration with MATLAB, allowing you to create and execute MATLAB scripts and functions through Claude or other MCP clients.
Setup Requirements
- Python 3.11 (Python 3.13 and 3.12 are not currently supported by MATLAB Engine)
- MATLAB R2024a (or compatible version)
- uv package manager
Installation
- Create and set up the Python environment:
# Pin Python version
uv python pin 3.11
# Create virtual environment
uv venv
# Activate virtual environment
source .venv/bin/activate
# Install MCP
uv add "mcp[cli]"
- Install MATLAB Engine
The MATLAB Engine will be installed automatically when the server first runs, using the MATLAB installation specified in the
MATLAB_PATHenvironment variable.
Directory Structure
matlab_server.py: The main MCP server implementationmatlab_scripts/: Directory where all MATLAB scripts and functions are saved (created automatically)pyproject.toml: Python project configuration.python-version: Specifies Python version for uv
Claude Desktop Integration
- Open your Claude Desktop configuration:
# On macOS
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
- Add the MATLAB server configuration:
{
"mcpServers": {
"matlab": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/matlab-mcp",
"run",
"matlab_server.py"
],
"env": {
"MATLAB_PATH": "/Applications/MATLAB_R2024a.app"
}
}
}
}
Make sure to:
- Replace
/absolute/path/to/matlab-mcpwith the actual path to your project directory - Verify the
MATLAB_PATHpoints to your MATLAB installation - Use absolute paths (not relative)
Features
The server provides several tools:
-
create_matlab_script: Create a new MATLAB script file- Scripts are saved in the
matlab_scriptsdirectory - File names must be valid MATLAB identifiers
- Scripts are saved in the
-
create_matlab_function: Create a new MATLAB function file- Functions are saved in the
matlab_scriptsdirectory - Must include valid function definition
- Functions are saved in the
-
execute_matlab_script: Run a MATLAB script and get results- Returns output text, generated figures, and workspace variables
- Can pass arguments to scripts
-
call_matlab_function: Call a MATLAB function with arguments- Returns function output and any generated figures
Testing
You can test the server using the MCP Inspector:
# Make sure you're in your virtual environment
source .venv/bin/activate
# Run the inspector
MATLAB_PATH=/Applications/MATLAB_R2024a.app mcp dev matlab_server.py
Example test script:
t = 0:0.01:2*pi;
y = sin(t);
plot(t, y);
title('Test Plot');
xlabel('Time');
ylabel('Amplitude');
Script Storage
- All MATLAB scripts and functions are saved in the
matlab_scriptsdirectory - This directory is created automatically when the server starts
- Files are named
<script_name>.mor<function_name>.m - The directory is in the same location as
matlab_server.py
Environment Variables
MATLAB_PATH: Path to your MATLAB installation- Default:
/Applications/MATLAB_R2024a.app - Set in Claude Desktop config or when running directly
- Default:
Troubleshooting
-
MATLAB Engine Installation Fails
- Verify MATLAB_PATH is correct
- Try installing engine manually:
cd $MATLAB_PATH/extern/engines/python python setup.py install
-
Python Version Issues
- Make sure you're using Python 3.11
- Check with:
python --version - Use
uv python pin 3.11if needed
-
Script Execution Errors
- Check the
matlab_scriptsdirectory exists - Verify script syntax is valid
- Look for error messages in MATLAB output
- Check the
Updates and Maintenance
- Keep your MATLAB installation updated
- Update Python packages as needed:
uv pip install --upgrade mcp[cli] - Check MATLAB engine compatibility when updating Python
Servidores relacionados
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
Data Engineering Tutor MCP Server
A tutor for Data Engineering that provides personalized updates on concepts, patterns, and technologies.
AgentDesk MCP
Adversarial AI quality review for LLM pipelines. Dual-reviewer consensus with anti-gaming protection. BYOK — works with Claude Code, Claude Desktop, and any MCP client.
AvaloniaUI
Tools, resources, and guidance for building cross-platform applications with AvaloniaUI.
MCP QEMU VM Control
Give your AI full computer access — safely. Let Claude (or any MCP-compatible LLM) see your screen, move the mouse, type on the keyboard, and run commands — all inside an isolated QEMU virtual machine. Perfect for AI-driven automation, testing, and computer-use experiments without risking your host system.
Replicate Flux MCP
Generate high-quality images and vector graphics using the Replicate API.
mcpproxy-go
Open-source local MCP proxy server. Routes multiple MCP servers through a single endpoint with BM25 tool filtering, quarantine security, activity logging, and web UI.
Swift MCP Server - JavaScript Version
Answers Swift and SwiftUI questions based on the '100 Days of SwiftUI' course using a local SQLite database.
Mindpilot MCP
Visualize legacy code and inspect complex flows to understand your agent's operations.
AgentSeal
Every agent action is recorded in a SHA-256 hash chain; with this, you can actually prove to clients that your agent did what it said it did