mcp-boilerplate

StreamlineDevelopers/mcp-boilerplate

3.2

If you are the rightful owner of mcp-boilerplate and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

MCP Boiler is a simple FastMCP server designed for various purposes, providing a flexible and efficient protocol server framework.

MCP Boilerplate

A simple FastMCP server for idk whatever fucking purpose you want!

Installation

  1. Make sure you have UV installed

This is how i installed it

pip install uv
  1. Clone it and set it up boys!
git clone https://github.com/StreamlineDevelopers/mcp-boilerplate.git

cd mcp-boilerplate

uv sync

Configuration

  1. Well just make an .env, I already have .env.example there
cp .env.example .env

USAAAAAAGE

  1. Run it baby
uv run python src/main.py

Want to try it?

import OpenAI from 'openai'; // Installed this please

const client = new OpenAI(
    {
        apiKey: "your-own-api-key-ofcourse"

    }
);

const resp = await client.responses.create({
    model: "gpt-4o",
    tools: [
        {
            type: "mcp",                                                                            // does matter. its the clear distinction for openai to a function call
            server_label: "dad-joke-server",                                                        // doesnt matter, but add it
            server_description: "Server that provides hilarious dad jokes for various topics.",     // Doesnt matter, but add it
            server_url: "https://d760adfe9655.ngrok-free.app/sse",                                  // this is the URL of your mcp server. you need to expose it via ngrok / port forwarding
            authorization: "ERBIyRqJP38reO4Y0L2aj0rQPfgVb0Lpoir8TUMNuvc",                           // this is the token to access your mcp server which is available on your own introspection server. if dont have ask me i guess
            require_approval: "never",                                                              // until this point i never changed this
        },
    ],
    input: "Good morning, I am Paul!",
});

console.log(resp.output_text)

That's it folks