MCP Auto Register
@JoshuaSiraj
About MCP Auto Register
Automate the registration of functions and classes from a python package into a FastMCP instance.
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP Auto Register?
MCP Auto Register is a Python package that automates the registration of functions and classes from any Python package into a FastMCP instance, exposing them as MCP tools or resources. It is designed for developers who want to quickly turn existing library code into MCP-enabled endpoints without manual wrapping.
How to use MCP Auto Register?
Install via pip install mcp-auto-register. Then use register_functions_from_package to register specific functions (e.g., from scipy.linalg) or register_classes_from_package with a custom wrapper (e.g., for nba_api.stats.endpoints) by passing an initialized FastMCP instance. The example uses transport="stdio" when running.
Key features of MCP Auto Register
- Automatically registers functions from a Python package into FastMCP
- Supports registering classes with a user-defined wrapper function
- Allows filtering which functions to include via
func_filter - Integrates directly with the FastMCP server instance
- Simple pip installation and minimal setup code
Use cases of MCP Auto Register
- Expose specific scientific computing functions (e.g., from
scipy.linalg) as MCP tools - Turn external API endpoint classes (e.g., from
nba_api) into MCP tools with a consistent interface - Quickly prototype MCP servers by reusing existing Python library code without manual scaffolding
- Automate registration of large packages where manual tool definition would be tedious
FAQ from MCP Auto Register
Which functions from a package can I register?
You can register any callable function or class method from an imported Python package. Use the func_filter parameter to specify function names (e.g., ['eigh', 'inv']) or leave it empty to register all public functions.
How do I register classes instead of functions?
Use register_classes_from_package and provide a wrapper function that takes an endpoint class instance and returns a callable. The wrapper can inspect the class’s __init__ parameters and return a function that FastMCP will expose.
What transport or communication protocol does the MCP server use?
The README example shows mcp.run(transport="stdio"), indicating stdio transport. FastMCP supports other transports (e.g., SSE), but only stdio is shown in the provided code.
Do I need FastMCP installed separately?
Yes, the code imports FastMCP from mcp.server.fastmcp. The package assumes you have FastMCP already installed in your environment; it does not bundle it.
Can I use this with any Python package?
The package works with any Python package that can be imported, provided the functions or classes you want to register are accessible. For classes, you must supply a wrapper that returns a valid callable for FastMCP.
More Other MCP servers
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Website
FunnyWolfAdversary simulation and Red teaming platform with AI

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Comments