MCPioneer 🚀
About
# MCPioneer 🚀 **Build Your Own Custom MCP Server for AI Agents** MCPioneer is a beginner-friendly project demonstrating how to create a custom MCP (Message/Command/Processing) server using Python. This server acts as a bridge to extend the capabilities of AI agents, allowing them to perform external tasks like calling…
Explore
- Beginner‑friendly demonstration of building an MCP server.
- Built with Python 3.10+ and MXGp Python SDK.
- Uses UV Package Manager for dependency management.
- Tested with Claude Desktop.
- Provides tools, resources, and services for AI agents.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCPioneer 🚀Command (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Windows:
``bash`
iwr -useb https://mirror.ghproxy.com/https://raw.githubusercontent.com/astral-sh/uv/main/scripts/install.ps1 | iex
- Mac/Linux:
bash``
curl -LsSf https://astral.sh/uv/install.sh | sh
bash
uv run mcp install main.py
- Go to Settings → Developer → Edit Config.
- Add your server to the configurations manually if necessary.
- Restart Claude Desktop if you don't see the MCP server immediately.
---
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcpioneer \ud83d\ude80": {
"Custom-MCP-Server-for-AI-Agents": {
"command": "uv",
"args": [
"init",
"."
]
}
}
}
}McpServers
{
"Custom-MCP-Server-for-AI-Agents": {
"command": "uv",
"args": [
"init",
"."
]
}
}📚 What is MCP?
An MCP server provides tools, resources, and services that AI agents can access to enhance their functionalities. Think of it as a "toolbox" that an AI can open whenever it needs external help beyond its basic capabilities. ---⚙️ Technologies Used
- Python 3.10+ - MXGp Python SDK - UV Package Manager - Claude Desktop (for testing) ---🚀 Getting Started
1. Install UV (Better Package Manager)
- Windows: ``bash
iwr -useb https://mirror.ghproxy.com/https://raw.githubusercontent.com/astral-sh/uv/main/scripts/install.ps1 | iex
`
- Mac/Linux:
`bash
curl -LsSf https://astral.sh/uv/install.sh | sh
`
2. Initialize Project
`bash
uv init .
uv add mcp cli
`
3. Create a Simple MCP Server
Example main.py:
`python
from mcp_servers.fast_mcp import FastMCP
server = FastMCP(name="DemoServer")
@server.tool
def add_numbers(a: int, b: int) -> int:
return a + b
@server.resource
def greet(name: str) -> str:
return f"Hello, {name}!"
server.run()
`
4. Install MCP Server into Claude Desktop
`bash
uv run mcp install main.py
`
5. Configure Claude Desktop
- Go to Settings → Developer → Edit Config.
- Add your server to the configurations manually if necessary.
- Restart Claude Desktop if you don't see the MCP server immediately.
---
🛠️ Project Structure
`
MCPioneer/
├── main.py
├── README.md
├── .venv/ (created automatically)
└── uv.toml
``
---
---
✨ Author
Created with ❤️ by Nithin.Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
