Skip to main content
Glama
rkram90

My UV MCP Server

by rkram90
README.md
# My UV MCP Server

This is a simple **Model Context Protocol (MCP) server** built using Python and the `uv` package manager.  
It demonstrates creating a basic MCP server with tools and connecting it to **Claude Desktop**.

---

## Quick Start

Follow these steps to set up and run the MCP server:

| Step | Command                    | Description                   |
| ---- | -------------------------- | ----------------------------- |
| 1    | `uv init my-mcp-server`    | Create new Python MCP project |
| 2    | `uv add mcp[cli]`          | Add MCP SDK with CLI          |
| 3    | `source venv/bin/activate` | Activate virtual environment  |
| 4    | `server.py`                | Write your server code        |
| 5    | `mcp dev server.py`        | Test and debug MCP server     |
| 6    | `mcp install server.py`    | Add it to Claude Desktop      |

---

## 1. Create the MCP Server

Create a file `server.py` with the following code:

```python
from mcp.server.fastmcp import FastMCP

mcp = FastMCP("My UV MCP Server")

@mcp.tool()
def greet(name: str) -> str:
    """Return a greeting message."""
    return f"Hello, {name}! 👋"

if __name__ == "__main__":
    mcp.run()
```

TDQS

A3.6/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'add_numbers' has a single, clearly defined purpose that cannot be confused with any other tool in this set.

Naming Consistency5/5

The single tool name 'add_numbers' follows a clear verb_noun pattern, and with only one tool, there is no inconsistency to evaluate. The naming is straightforward and predictable in isolation.

Tool Count2/5

A single tool is too few for most practical server purposes, as it severely limits functionality and scope. This feels thin and inadequate for handling any meaningful domain beyond a trivial operation, indicating a poor fit for typical MCP server use cases.

Completeness1/5

The server's purpose is unclear from the single tool, making it impossible to assess coverage meaningfully. With only a basic arithmetic operation, there are significant gaps in any plausible domain, rendering the tool surface severely incomplete for practical agent workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues