mcpField
M
MCP Lab

MCP Lab

Local
github.com/LPFerreira33Developer Tools0Updated 21w ago
Repository

About MCP Lab

MCP Lab is a Python project for experimenting with MCP, aimed at developers who want a modular server and client setup. Reusable tool modules are automatically registered and can be extended with Python functions.

Key features

  1. 01Modular Python server and client
  2. 02Reusable tool modules
  3. 03Automatic tool registration
  4. 04Add tools with Python functions

Use cases

  1. 01Experimenting with MCP in Python
  2. 02Adding custom tools to an MCP server

MCP support

It includes an MCP server and client. The server exposes reusable, automatically registered tools to MCP clients.

#mcp-lab#modular-setup#python-experimentation

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Lab

This repository contains a modular setup for experimenting with MCP in Python. It includes both a server and a client, as well as reusable tool modules.

Project Structure

mcp/
├── mcp_server/      # MCP server implementation and tools
│   ├── server.py
│   ├── requirements.txt
│   ├── README.md
│   └── tools/
│       └── ...
├── mcp_client/      # MCP client implementation
│   ├── client.py
│   ├── client_llm.py
│   ├── requirements.txt
│   ├── README.md
│   └── .env
├── LICENSE
└── README.md        # (This file)

Quick Start

1. Clone the repository
git clone https://github.com/LPFerreira33/mcp-lab.git
cd mcp-lab
2. Set up the server
cd mcp_server
python -m venv .venv
source .venv/bin/activate
uv pip install -r requirements.txt
uv run server.py
3. Set up the client
cd mcp_client
python -m venv .venv
.venv\Scripts\activate
uv pip install -r requirements.txt
# Edit .env to match your server's IP and port if needed
python client.py

Tool Modules

Reusable tools are organized in mcp_server/tools/ and are automatically registered by the server. You can add your own tools by creating new Python functions in these modules.

License

This project is licensed under the MIT License. See LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.