In the companion article Create and Deploy a FastMCP Server on macOS you built a FastMCP server and deployed it as a launchd service listening on http://127.0.0.1:8000/mcp/. This tutorial builds the other half: a command-line MCP client that connects to that running server over HTTP, lists what it offers, and calls its tools. Because you are on a Mac, the client does one extra thing that a generic client does not: with --copy it drops a tool’s result straight onto the macOS clipboard via pbcopy, so the output of slugify is ready to paste into your editor. Everything is managed with uv and make. ...

The Model Context Protocol (MCP) lets AI clients (Claude Desktop, Claude Code, or your own agent) call tools, read resources, and load prompts from an external server. FastMCP is a Python framework that turns ordinary typed functions into a compliant MCP server with a couple of decorators. Most FastMCP tutorials stop at “run it over stdio.” This one goes further: you build a small server, then deploy it as a persistent background service on your Mac using launchd, the same supervisor macOS uses for its own daemons. The result is an HTTP MCP server that starts at login, restarts if it crashes, and writes logs you can tail — managed entirely through make. ...

A single LLM agent works well until the job spans several distinct skills. The proven pattern is a coordinator agent that delegates to specialized sub-agents — much like a manager routing work to departments. Google’s Agent Development Kit (ADK) is a code-first Python framework built for exactly this: you define agents and plain-Python tools, wire specialists under a coordinator, and ADK handles the LLM-driven delegation between them. In this tutorial you will build a travel concierge: a coordinator agent that routes weather questions to a weather specialist and currency questions to a currency specialist, each backed by its own tool. You will run it in the terminal and the ADK web UI, then cover the deterministic parts (the tools and the agent wiring) with pytest, no API key required. ...

A Model Context Protocol (MCP) server exposes tools, resources, and prompts; an MCP client is what connects to that server, discovers those capabilities, and calls them. Clients are usually embedded in an AI application (Claude Desktop, Claude Code, or your own agent), but writing a standalone client is the clearest way to understand the protocol and to script, test, or debug a server. In this tutorial you will build a command-line MCP client with FastMCP. It connects to any MCP server over stdio, prints the server’s advertised tools, resources, and prompts, and calls a tool with JSON arguments. You will run it against a small demo server, then cover it with pytest using FastMCP’s in-memory transport — no subprocess required. ...

The Model Context Protocol (MCP) is an open standard that lets AI clients (such as Claude Desktop, Claude Code, or your own agent) call tools, read resources, and load prompts from an external server over a well-defined wire protocol. FastMCP is a Python framework that hides the protocol plumbing behind plain decorators, so you write ordinary typed functions and FastMCP turns them into a compliant server. In this tutorial you will build a small but realistic “notes” MCP server: it exposes tools to create and search notes, a resource to read a single note by URI, and a prompt that asks the model to summarize a note. You will run it over stdio, inspect it interactively, and cover it with pytest using FastMCP’s in-memory client. ...

A minimal Rust project that prints a greeting, accepts a name from the command line, includes a test suite, and uses a Makefile to drive common tasks. This tutorial covers project setup with Cargo, module organization, argument parsing with std::env, unit tests, and build automation. Prerequisites Rust 1.70 or later (install via rustup) A Unix-like terminal (macOS, Linux, or WSL on Windows) make installed (pre-installed on macOS and most Linux distributions) No third-party crates required Step 1: Create the project with Cargo Create the file cargo new hello-world Detailed breakdown cargo new hello-world scaffolds a new Rust project with a Cargo.toml manifest and a src/main.rs entry point. When run outside an existing Git repository, Cargo also initializes a new Git repo and generates a .gitignore. When run inside an existing repo (as in this tutorial), it skips Git initialization. The project name hello-world becomes both the directory name and the package name in Cargo.toml. Step 2: Update the gitignore The default Cargo .gitignore only excludes target/. Add common temporary artifacts. ...

A minimal TypeScript project that prints a greeting, accepts a name from the command line, includes a test suite using Vitest, and uses a Makefile to drive common tasks. This tutorial covers project setup, TypeScript configuration, argument parsing, unit testing, and build automation. Prerequisites Node.js 20 or later npm 9 or later A Unix-like terminal (macOS, Linux, or WSL on Windows) make installed (pre-installed on macOS and most Linux distributions) Step 1: Set up the project structure Create the file mkdir -p hello-world touch hello-world/.gitignore Add the code: hello-world/.gitignore node_modules/ dist/ .DS_Store *.log tmp/ Detailed breakdown node_modules/ excludes installed dependencies, which are restored with npm install. dist/ excludes compiled TypeScript output generated by the build step. .DS_Store, *.log, and tmp/ cover common OS and temporary artifacts. Step 2: Initialize the project and install dependencies Create the file cd hello-world npm init -y Install TypeScript and the test framework as development dependencies: ...

A minimal Go project that prints a greeting, accepts a name from the command line, includes a test suite, and uses a Makefile to drive common tasks. This tutorial covers project structure, flag parsing, table-driven tests, and build automation. Prerequisites Go 1.22 or later A Unix-like terminal (macOS, Linux, or WSL on Windows) make installed (pre-installed on macOS and most Linux distributions) No third-party packages required Step 1: Set up the project structure Create the file mkdir -p hello-world touch hello-world/.gitignore Add the code: hello-world/.gitignore bin/ *.test *.out .DS_Store *.log tmp/ Detailed breakdown bin/ excludes compiled binaries produced by the build step. *.test and *.out exclude Go test binaries and coverage output files. .DS_Store, *.log, and tmp/ cover common OS and temporary artifacts. Step 2: Initialize the Go module Create the file cd hello-world go mod init hello-world Detailed breakdown go mod init hello-world creates a go.mod file that declares the module path as hello-world. All import paths within the project use this prefix. Since the project uses only the standard library, no dependencies are added to go.mod. Step 3: Create the greeter package This package contains the core greeting logic, separated from the entry point so it can be tested independently. ...

A minimal Python project that prints a greeting, accepts a name from the command line, includes a pytest test suite, and uses a Makefile to drive common tasks. This tutorial covers project setup with uv, argument parsing, testing with pytest, and automation for a simple but complete workflow. Prerequisites Python 3.10 or later uv 0.4 or later (curl -LsSf https://astral.sh/uv/install.sh | sh) A Unix-like terminal (macOS, Linux, or WSL on Windows) make installed (pre-installed on macOS and most Linux distributions) Step 1: Initialize the project with uv Create the file uv init hello-world cd hello-world Detailed breakdown uv init hello-world scaffolds a new Python project with a pyproject.toml, a main.py sample file, and a .python-version file. pyproject.toml serves as the project manifest, replacing the need for setup.py or requirements.txt. uv automatically creates a .venv virtual environment on first run. Step 2: Add pytest and set up the project Create the file Remove the generated sample file and add pytest as a dev dependency: ...

A command-line task manager that stores tasks in a local JSON file, supports adding, listing, completing, and deleting tasks, and uses only the Python standard library. Prerequisites Python 3.10 or later uv 0.4 or later (curl -LsSf https://astral.sh/uv/install.sh | sh) A Unix-like terminal (macOS, Linux, or WSL on Windows) make installed (pre-installed on macOS and most Linux distributions) Step 1: Set up the project structure Create the file uv init cli-task-manager cd cli-task-manager rm main.py README.md uv add --dev pytest Add the code: .gitignore __pycache__/ *.pyc .venv/ .pytest_cache/ *.egg-info/ dist/ build/ .DS_Store *.log tmp/ tasks.json Detailed breakdown uv init cli-task-manager scaffolds a new Python project with a pyproject.toml, a main.py sample file, and a .python-version file. rm main.py README.md removes the placeholder files since the project will use its own package structure. uv add --dev pytest installs pytest and records it under [dependency-groups] in pyproject.toml. __pycache__/ and *.pyc exclude Python bytecode files generated at runtime. .venv/ excludes the virtual environment that uv manages locally. tasks.json is excluded because it is runtime data, not source code. Each user generates their own task file. .DS_Store and tmp/ cover common OS and temporary artifacts. Step 2: Create the task storage module This module handles all persistence — reading and writing tasks to a JSON file on disk. ...