# Add the server (replace with your actual binary path)
claude mcp add --transport stdio matlab -- /path/to/matlab-mcp-core-server

# With custom working folder
claude mcp add --transport stdio matlab -- /path/to/matlab-mcp-core-server --initial-working-folder=/home/user/myproject

# With nodesktop mode
claude mcp add --transport stdio matlab -- /path/to/matlab-mcp-core-server --matlab-display-mode=nodesktop

{
    "servers": {
        "matlab": {
            "type": "stdio",
            "command": "/path/to/matlab-mcp-core-server",
            "args": [
                "--initial-working-folder=/home/user/projects",
                "--matlab-display-mode=nodesktop"
            ]
        }
    }
}

{
    "servers": {
        "matlab": {
            "type": "stdio",
            "command": "C:\\Program Files\\matlab-mcp-core-server\\matlab-mcp-core-server-win64.exe",
            "args": [
                "--initial-working-folder=C:\\Users\\username\\projects",
                "--initialize-matlab-on-startup=true"
            ]
        }
    }
}

# Specify MATLAB installation
--matlab-root=/usr/local/MATLAB/R2026a
# Environment variable: MW_MCP_SERVER_MATLAB_ROOT

# Set initial working directory
--initial-working-folder=/home/user/myproject
# Environment variable: MW_MCP_SERVER_INITIAL_WORKING_FOLDER

# Display mode: desktop or nodesktop
--matlab-display-mode=nodesktop
# Environment variable: MW_MCP_SERVER_MATLAB_DISPLAY_MODE

# Initialize MATLAB immediately on startup
--initialize-matlab-on-startup=true
# Environment variable: MW_MCP_SERVER_INITIALIZE_MATLAB_ON_STARTUP

# Connect to existing MATLAB session (R2023a+)
--matlab-session-mode=existing
# Environment variable: MW_MCP_SERVER_MATLAB_SESSION_MODE

# Setup for existing session mode (run once)
./matlab-mcp-core-server --setup-matlab

# Custom tools definition
--extension-file=/path/to/my-tools.json
# Environment variable: MW_MCP_SERVER_EXTENSION_FILE

# Log configuration
--log-folder=/tmp/matlab-mcp-logs
--log-level=debug
# Environment variables: MW_MCP_SERVER_LOG_FOLDER, MW_MCP_SERVER_LOG_LEVEL

# Disable telemetry
--disable-telemetry=true
# Environment variable: MW_MCP_SERVER_DISABLE_TELEMETRY

MATLAB Version: R2026a
Installed Toolboxes:
- Signal Processing Toolbox (9.3)
- Image Processing Toolbox (12.0)
- Deep Learning Toolbox (24.1)

Script: /home/user/projects/calculate_fft.m

Analysis results:
- Line 15: Variable 'N' is defined but never used
- Line 23: Use of deprecated function 'fft2'. Consider 'fft' instead
- Line 45: Missing semicolon may cause unwanted output
- Performance: Consider preallocating array at line 12

x = linspace(0, 2*pi, 100);
y = sin(x);
plot(x, y);
title('Sine Wave');

A = [1 2 3; 4 5 6; 7 8 9];
B = inv(A' * A) * A';
disp('Moore-Penrose pseudoinverse:');
disp(B);

fs = 1000;
t = 0:1/fs:1-1/fs;
signal = sin(2*pi*50*t) + 0.5*sin(2*pi*120*t);
fft_result = fft(signal);
power = abs(fft_result).^2/length(signal);
fprintf('Signal power: %.4f\n', sum(power));

% Load and process experimental data
data = load('experiment_results.mat');
temperature = data.temperature;
pressure = data.pressure;

% Remove outliers
temp_clean = rmoutliers(temperature);
press_clean = rmoutliers(pressure);

% Calculate statistics
mean_temp = mean(temp_clean);
std_temp = std(temp_clean);
mean_press = mean(press_clean);

% Create visualization
figure;
subplot(2,1,1);
histogram(temp_clean, 30);
title(sprintf('Temperature Distribution (μ=%.2f, σ=%.2f)', mean_temp, std_temp));
xlabel('Temperature (°C)');

subplot(2,1,2);
scatter(temp_clean, press_clean);
title('Pressure vs Temperature');
xlabel('Temperature (°C)');
ylabel('Pressure (kPa)');

% Save results
results.mean_temperature = mean_temp;
results.mean_pressure = mean_press;
results.correlation = corrcoef(temp_clean, press_clean);
save('processed_results.mat', 'results');

fprintf('Processing complete. Results saved.\n');

User: "Load the data from sensor_readings.csv and plot it"

AI uses: evaluate_matlab_code
Code: 
data = readtable('sensor_readings.csv');
plot(data.Time, data.Value);
xlabel('Time'); ylabel('Sensor Reading');
grid on;

User: "Check my simulation script for issues before running it"

AI uses: check_matlab_code (script_path: /home/user/simulation.m)
Then: Suggests fixes
Then: evaluate_matlab_code (to run corrected version)

% Step 1: Load and prepare data
data = readmatrix('measurements.csv');
x = data(:,1);
y = data(:,2);

% Step 2: Fit polynomial model
p = polyfit(x, y, 3);
y_fit = polyval(p, x);

% Step 3: Calculate residuals and R-squared
residuals = y - y_fit;
ss_res = sum(residuals.^2);
ss_tot = sum((y - mean(y)).^2);
r_squared = 1 - (ss_res / ss_tot);

% Step 4: Visualize results
figure;
plot(x, y, 'o', 'DisplayName', 'Data');
hold on;
plot(x, y_fit, '-', 'LineWidth', 2, 'DisplayName', 'Fit');
legend('show');
title(sprintf('Polynomial Fit (R² = %.4f)', r_squared));

# Install the MCP toolbox in MATLAB
./matlab-mcp-core-server --setup-matlab --matlab-root=/usr/local/MATLAB/R2026a

% Share this MATLAB session with MCP
shareMATLABSession()

{
    "servers": {
        "matlab": {
            "type": "stdio",
            "command": "/path/to/matlab-mcp-core-server",
            "args": ["--matlab-session-mode=existing"]
        }
    }
}

# Explicitly specify MATLAB root
--matlab-root=/usr/local/MATLAB/R2026a

# Or add MATLAB to PATH
export PATH="/usr/local/MATLAB/R2026a/bin:$PATH"

chmod +x ~/Downloads/matlab-mcp-core-server

figure;
plot(x, y);
saveas(gcf, 'output.png');

# Correct
script_path: /home/user/projects/analysis.m

# Incorrect (relative paths may fail)
script_path: ../analysis.m

% Process data in chunks
chunk_size = 1000;
for i = 1:chunk_size:length(data)
    chunk = data(i:min(i+chunk_size-1, end));
    process_chunk(chunk);
end

% Clear variables when done
clear large_array;

# Specify custom log location
--log-folder=/home/user/matlab-logs --log-level=debug

# Default locations:
# Linux/macOS: /tmp
# Windows: C:\Users\username\AppData\Local\Temp

# Core configuration
export MW_MCP_SERVER_MATLAB_ROOT="/usr/local/MATLAB/R2026a"
export MW_MCP_SERVER_INITIAL_WORKING_FOLDER="/home/user/projects"
export MW_MCP_SERVER_MATLAB_DISPLAY_MODE="nodesktop"
export MW_MCP_SERVER_MATLAB_SESSION_MODE="existing"
export MW_MCP_SERVER_INITIALIZE_MATLAB_ON_STARTUP="true"

# Advanced options
export MW_MCP_SERVER_EXTENSION_FILE="/path/to/tools.json"
export MW_MCP_SERVER_LOG_FOLDER="/var/log/matlab-mcp"
export MW_MCP_SERVER_LOG_LEVEL="info"
export MW_MCP_SERVER_DISABLE_TELEMETRY="true"