MCP Autojob Server

🚀 MCP Server Building Guide

This guide provides a comprehensive approach to achieving office automation through the construction of an MCP server. It details the planning, implementation, and testing processes, ensuring a smooth and efficient setup.

📋 Plan

To achieve office automation, the following steps are taken:

• Check my daily schedule after arriving at work each morning.
• Check the weather for the day and send notifications.
• Review the list of emails awaiting replies.
• List the incomplete tasks assigned to me in the collaboration tool Jira.

🚀 Quick Start

📦 Installation

The following commands are used to install and set up the MCP server environment:

# Install uv
brew install uv

uv init [mcp-server-name] --python 3.12 # Specify the version
cd [mcp-server-name]
uv venv # Install the .venv virtual environment
source .venv/bin/activate
uv add "mcp[cli]"

# Install the toml file (package)
cat pyproject.toml

# Create the server.py file
touch server.py

# Install cursor
brew install --cask cursor
cursor .

## Execute commands in cursor
Open the cursor application -> Press cmd + shift + p -> Execute Shell Command: Install the 'cursor' command

# Add cursor documents
Go to Cursor settings -> Features -> Documents > Click "+ Add New Document" ->
- MCP Official Website (https://modelcontextprotocol.io/)
- MCP llm.txt (https://modelcontextprotocol.io/llms-full.txt)
- MCP Python SDK (https://github.com/modelcontextprotocol/python-sdk)

# Configure cursor rules
Refer to https://cursor.directory/fastapi-python-microservices-serverless-cursor-rules
-> Execute the npx copy command: npx cursor-directory rules add fastapi-python-microservices-serverless-cursor-rules
-> Perform the configuration in the terminal

# Run independently
mcp dev server.py
mcp install server.py (After running, you can check agent cursor, claude)

🐳 Docker (For server subscription)

The following Docker commands are used for building images, starting containers, and managing the server:

# Build the image and start the container (run in the background)
$ docker compose up -d --build

# View logs (for background running)
$ docker compose logs -f

# Stop the server
$ docker compose down

# Execute simultaneously
$ docker compose down & docker compose up -d --build & docker compose logs -f

📚 structlog Installation

uv pip install structlog

🧪 Unit Testing

uv pip install python-dotenv
uv pip install pytest requests

# Run tests one by one
pytest test/test_github_tool.py
# Run all tests
pytest -v -s