Custom Tools

Custom Tools

Expose your own MATLAB functions as first-class MCP tools. AI agents can discover and call them directly, with full parameter validation and help text.

How It Works

1. Write your MATLAB function (.m file)
2. Describe it in custom_tools.yaml
3. The server registers it as an MCP tool at startup
4. Agents see it alongside built-in tools

Configuration

Point your config.yaml to the custom tools file:

custom_tools:
  config_file: "./custom_tools.yaml"

YAML Schema

Each tool definition in custom_tools.yaml must include:

tools:
  - name: tool_name                    # MCP tool name (what agents call)
    matlab_function: pkg.func          # MATLAB function to call
    description: "What it does"        # Shown to agents
    parameters:                        # List of parameter definitions
      - name: param_name
        type: string                   # Parameter type (see table below)
        required: true                 # or false
        description: "What this parameter does"  # Optional, shown to agents
      - name: optional_param
        type: double
        default: 1.0                   # Default value if not provided
    returns: "Description of return value"  # What the function returns

Parameter Types

YAML Type	Aliases	Python Type	Notes
string	str	str	Text input
float	number	float	Floating-point numbers
double	—	float	Alias for float
int	integer	int	Integer numbers
bool	boolean, logical	bool	True/false values
list	—	list	Array/list input
dict	—	dict	Structured data (key-value)
any	—	Any	Accept any type

Complete Example

1. MATLAB Function (mylib/analyze_signal.m)

function result = analyze_signal(signal_path, sample_rate, window_size)
    % ANALYZE_SIGNAL  Frequency analysis of a signal file
    %
    %   result = analyze_signal(signal_path, sample_rate, window_size)
    %
    %   Returns struct with: frequencies, magnitudes, snr, peaks

    data = load(signal_path);
    signal = data.signal;

    N = length(signal);
    Y = fft(signal, window_size);
    f = (0:window_size/2-1) * sample_rate / window_size;
    mag = abs(Y(1:window_size/2)) / N;

    [peaks, locs] = findpeaks(mag, 'MinPeakHeight', max(mag)*0.1);

    result.frequencies = f;
    result.magnitudes = mag;
    result.snr = snr(signal);
    result.peaks = struct('frequencies', f(locs), 'amplitudes', peaks);
end

2. Custom Tool Definition (custom_tools.yaml)

tools:
  - name: analyze_signal
    matlab_function: mylib.analyze_signal
    description: >
      Analyze a signal file and return frequency components, SNR,
      and peak detection results.
    parameters:
      - name: signal_path
        type: string
        required: true
        description: "Path to the signal data file (.mat)"
      - name: sample_rate
        type: double
        required: true
        description: "Sample rate in Hz"
      - name: window_size
        type: int
        default: 1024
        description: "FFT window size"
    returns: "Struct with fields: frequencies, magnitudes, snr, peaks"

3. Make Sure MATLAB Can Find It

Add the directory containing your .m files to the workspace paths in config.yaml:

workspace:
  default_paths:
    - "/path/to/mylib"

4. Agent Usage

The agent now sees analyze_signal as a tool and can call it:

"Analyze the signal in data/recording.mat at 44100 Hz sample rate"

The server:

1. Validates parameters against the YAML schema
2. Calls analyze_signal('data/recording.mat', 44100, 1024) in MATLAB
3. Returns the result to the agent

Loading and Registration at Startup

When the MATLAB MCP server starts:

1. Config Loading: The server reads custom_tools.config_file from config.yaml
2. YAML Parsing: load_custom_tools() parses the YAML file and validates each tool definition using CustomToolDef pydantic model
3. Parameter Validation: Each parameter is validated:
   • Type must be a recognized YAML type (string, int, float, bool, list, dict, any)
   • Required parameters must not have defaults
   • Default values are type-checked
4. Handler Generation: For each valid tool, make_custom_tool_handler() creates an async handler function with:
   • Proper inspect.Signature for FastMCP introspection
   • Parameter validation using type hints
   • Error handling and structured error responses
5. Tool Registration: Each handler is registered with FastMCP as a tool, making it discoverable by agents

Error Handling:

• If the YAML file is missing, an empty tool list is returned (no error)
• If a tool definition is invalid, a warning is logged and that tool is skipped
• If a MATLAB function throws an error, the server returns a structured error response to the agent

Multiple Tools

tools:
  - name: analyze_signal
    matlab_function: mylib.analyze_signal
    description: "Frequency analysis of signal files"
    parameters:
      - name: signal_path
        type: string
        required: true
        description: "Path to the signal data file (.mat)"
    returns: "Frequency analysis struct"

  - name: train_model
    matlab_function: ml.train_classifier
    description: "Train a classification model"
    parameters:
      - name: dataset_path
        type: string
        required: true
        description: "Path to the training data (.mat or .csv)"
      - name: model_type
        type: string
        default: "svm"
        description: "Model type: svm, tree, knn, ensemble"
      - name: validation_split
        type: double
        default: 0.2
        description: "Fraction of data to use for validation (0-1)"
    returns: "Trained model and accuracy metrics"

  - name: process_image
    matlab_function: imgtools.enhance_image
    description: "Image enhancement pipeline"
    parameters:
      - name: image_path
        type: string
        required: true
        description: "Path to the input image"
      - name: denoise_strength
        type: double
        default: 0.5
        description: "Denoising strength (0=none, 1=maximum)"
      - name: sharpen
        type: logical
        default: false
        description: "Apply sharpening filter"
    returns: "Enhanced image saved to temp directory"

  - name: compute_statistics
    matlab_function: stats.compute_summary
    description: "Compute summary statistics for a .mat data file"
    parameters:
      - name: data_path
        type: string
        required: true
        description: "Path to the .mat file containing the data variable"
    returns: "Struct with mean, std, median, min, max, histogram data"

Tips

• Function names with packages: Use pkg.func notation to call functions in MATLAB packages (e.g., +mylib/analyze_signal.m → mylib.analyze_signal)
• MEX files: Custom tools work with .mex files too — just reference the function name without the extension
• Parameter descriptions: Include a description field for each parameter to help agents understand what each parameter does
• Type consistency: Ensure parameter types match MATLAB function expectations. Use logical for MATLAB boolean values
• Error handling: If the MATLAB function throws an error, the MCP server returns a structured error response to the agent
• Testing: Test your functions in MATLAB first before exposing them as tools
• Return value documentation: Provide clear returns descriptions so agents understand what to expect