Sales MCP Server

A Model Context Protocol (MCP) server that provides sales data tools, resources, and prompts to AI assistants.

What is This?

This MCP server gives AI assistant, Cline, the ability to:

• Fetch real sales data for different quarters
• Access available quarter information
• Generate sales analysis prompts

Project Structure

MCP/
├── app/
│   ├── server.py              # Main MCP server
│   ├── tools/
│   │   └── sales_tools.py     # Sales data functions
│   ├── resources/
│   │   └── sales_resources.py # Available quarters
│   └── prompts/
│       └── sales_prompts.py   # Sales analyst prompts
├── config/
│   └── settings.py            # Configuration
├── .venv/                     # Virtual environment
├── pyproject.toml             # Project dependencies
└── test_server.py             # Test script

Setup Instructions

1. Create Virtual Environment

python -m venv .venv
source .venv/Scripts/activate  # Windows Git Bash
# or
.venv\Scripts\activate         # Windows CMD

2. Install Dependencies

# Install uv (fast Python package manager)
python -m pip install uv

# Install MCP and FastMCP
pip install mcp
uv pip install fastmcp

3. Create Project Configuration

Create a pyproject.toml file:

[project]
name = "sales-mcp"
version = "0.0.0"
dependencies = []

[dependency-groups]
dev = [
    "mcp",
]

4. Add MCP as Dev Dependency

uv add --dev mcp

Testing Your Server

Option 1: Test Functions Directly

python test_server.py

Option 2: Run the Server

uv run fastmcp run app/server.py

Using with AI Clients

Cline (VS Code Extension) - RECOMMENDED

1. Install Cline extension in VS Code
2. Add to Cline's MCP config at: C:\Users\<YourName>\AppData\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json

{
  "mcpServers": {
    "sales-mcp": {
      "command": "C:\\Users\\<YourName>\\MCP\\.venv\\Scripts\\fastmcp.exe",
      "args": [
        "run",
        "C:\\Users\\<YourName>\\MCP\\app\\server.py"
      ]
    }
  }
}

3. Reload VS Code
4. Ask Cline: "What are the available quarters?"

## Available Tools

### `get_total_sales(quarter: str)`
Get sales data for a specific quarter.

**Example:**
```python
get_total_sales("Q1")
# Returns: {'quarter': 'Q1', 'total_sales': 120000}

Resource: list_quarters()

Returns available quarters: ["Q1", "Q2", "Q3"]

Prompt: sales_summary_prompt(quarter: str)

Generates a sales analyst prompt for the specified quarter.

Key Technical Details

• FastMCP: Uses the FastMCP framework for easy MCP server creation
• Resources: URI format resource://sales/quarters (must be valid URL)
• Transport: STDIO (standard input/output) for client communication
• Python Version: >=3.11

Troubleshooting

Server won't start:

• Make sure you're in the virtual environment
• Check that all dependencies are installed: pip list | grep mcp

Next Steps

Want to extend this server? Add more tools:

• Sales forecasting
• Customer analytics
• Product performance
• Revenue calculations
• Data visualization helpers

Each tool is just a Python function that AI can call!

Repository

GitHub: https://github.com/usafhulk/MCP