What is Mcp Auto Register

mcp_auto_register is a Python package that automates the registration of functions and classes from a specified Python package into a FastMCP instance, streamlining the integration process.

Use cases

Use cases for mcp_auto_register include automating the registration of mathematical functions from libraries like SciPy, or integrating API endpoints from sports statistics libraries, enabling seamless access to complex functionalities within a FastMCP environment.

How to use

To use mcp_auto_register, install it via pip with ‘pip install mcp-auto-register’. Then, you can register functions or classes from a package by importing the relevant functions and initializing a FastMCP instance, followed by calling the registration functions with the desired package and instance.

Key features

Key features of mcp_auto_register include automatic registration of functions and classes, support for filtering specific functions, and the ability to wrap classes for enhanced functionality.

Where to use

mcp_auto_register can be used in various fields such as data science, machine learning, and any application that requires the integration of Python packages into a FastMCP framework.

MCP Auto Register

This package automates the registration of functions and classes from a python package into a FastMCP instance.

Installation

To install the package, run the following command:

pip install mcp-auto-register

Usage

Register functions from a package:

from mcp_auto_register.register import register_functions_from_package
from mcp.server.fastmcp import FastMCP

# Initialize MCP instance
mcp_instance = FastMCP()

register_functions_from_package('scipy.linalg', mcp_instance=mcp_instance, func_filter=['eigh', 'inv'])

if __name__ == "__main__":
    mcp_instance.run()

Register classes from a package:

import inspect

from mcp_auto_register.register import register_classes_from_package
from mcp.server.fastmcp import FastMCP

from nba_api.stats.endpoints._base import Endpoint

# Create MCP instance
mcp = FastMCP()

def nba_endpoint_wrapper(endpoint: Endpoint):
    init_params = inspect.signature(endpoint.__init__).parameters
    required_args = {
        p: param.annotation if param.annotation != inspect.Parameter.empty else "Any"
        for p, param in init_params.items()
        if p != "self" and param.default == inspect.Parameter.empty
    }
    def wrapper(**kwargs):
        return endpoint(**kwargs).get_dict()
    
    wrapper.__signature__ = inspect.Signature(
        parameters=[
            inspect.Parameter(arg, inspect.Parameter.POSITIONAL_OR_KEYWORD)
            for arg, _ in required_args.items()
        ]
    )
    return wrapper

register_classes_from_package("nba_api.stats.endpoints", nba_endpoint_wrapper, mcp)

if __name__ == "__main__":
    mcp.run(transport="stdio")