Jez MCP Server

A FastMCP server with utility tools and resources, ready for deployment on FastMCP Cloud.

Features

Tools

• hello - Greet someone by name
• roll_dice - Roll dice with configurable sides and count
• calculate - Perform basic math operations (add, subtract, multiply, divide)
• get_timestamp - Get current timestamp in various formats (ISO, Unix, readable)
• text_stats - Analyze text and return statistics

Resources

• info://server - Server information and metadata
• config://features - Available features and configuration
• data://sample - Sample data for testing

Prompts

• greeting - Generate personalized greeting prompts
• analyze - Generate analysis prompts for topics

Local Development

Prerequisites

• Python 3.8+
• pip or uv package manager

Installation

1. Clone this repository:

git clone <your-repo-url>
cd fastmcp-server

2. Install dependencies:

pip install -r requirements.txt
# or using uv
uv pip install -r requirements.txt

3. Run the server locally:

python server.py
# or using fastmcp CLI
fastmcp run server.py

Testing with FastMCP Client

import asyncio
from fastmcp import Client

async def test_server():
    async with Client("server.py") as client:
        # List available tools
        tools = await client.list_tools()
        print(f"Available tools: {[t.name for t in tools]}")
        
        # Call a tool
        result = await client.call_tool("hello", {"name": "World"})
        print(f"Result: {result.data}")

asyncio.run(test_server())

Deployment to FastMCP Cloud

Step 1: Push to GitHub

1. Create a new repository on GitHub
2. Push this code to your repository:

git init
git add .
git commit -m "Initial commit"
git branch -M main
git remote add origin https://github.com/YOUR_USERNAME/YOUR_REPO.git
git push -u origin main

Step 2: Deploy on FastMCP Cloud

1. Visit fastmcp.cloud
2. Sign in with your GitHub account
3. Click "Create Project"
4. Select your repository
5. Configure:
   • Project Name: Your desired project name
   • Python File: server.py
   • Authentication: Configure as needed (optional)
6. Click "Deploy"

Step 3: Access Your Server

• Your server will be available at: https://YOUR_PROJECT.fastmcp.cloud
• The MCP endpoint will be: https://YOUR_PROJECT.fastmcp.cloud/mcp/

Features

• Automatic Deployment: Push to main branch triggers deployment
• Pull Request Previews: Each PR gets a unique preview URL
• Free During Beta: Currently free while in beta

Connecting to MCP Clients

Claude Desktop

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "jez-server": {
      "url": "https://YOUR_PROJECT.fastmcp.cloud/mcp/",
      "transport": "http"
    }
  }
}

Using with APIs

Anthropic API

import anthropic

client = anthropic.Anthropic()
response = client.beta.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Roll some dice!"}],
    mcp_servers=[{
        "type": "url",
        "url": "https://YOUR_PROJECT.fastmcp.cloud/mcp/",
        "name": "jez-server"
    }],
    extra_headers={"anthropic-beta": "mcp-client-2025-01-01"}
)

Environment Variables

If you need to use environment variables, create a .env file:

API_KEY=your_api_key
DEBUG=true

Then deploy with:

fastmcp install claude-desktop server.py --env-file .env

Author

Jeremy Dawes
CEO, Jezweb
Email: jeremy@jezweb.net
Website: www.jezweb.com.au

License

MIT