MCP Code Guidance

@JavaPentesters

Basic information

About MCP Code Guidance

这是一个使用 Python 语言从 0 到 1 搭建 MCP server 的代码学习教程

MCP Code Guidance config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-code-guidance": {
      "command": "python",
      "args": [
        "-m",
        "http.server",
        "8181"
      ]
    }
  }
}

MCP Code Guidance tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-code-guidance?

mcp-code-guidance is a tutorial for learning the MCP (Model Context Protocol) and A2A (Agent-to-Agent) protocol from scratch using Python. It focuses on the interaction between agents and external tools as well as collaboration between agents, and provides example MCP server implementations and a detailed tutorial.

How to use mcp-code-guidance?

Clone or download the repository, ensure Python 3.10+ and the uv package manager are installed. Then navigate into a specific example directory (e.g., mcp-server-01quickstart) and run uv init, uv venv, source .venv/bin/activate, and uv add "mcp[cli]" httpx to set up the environment. Detailed steps are provided in the README for each example.

Key features of mcp-code-guidance

Provides step‑by‑step tutorials for MCP and A2A protocols
Includes multiple ready‑to‑run MCP server examples (quickstart, weather, stock)
Uses Python 3.10+ and the FastMCP library
Managed with uv for clean project isolation
Covers the three MCP capabilities: Tool, Resource, and Prompt
Licensed under MIT for open‑source use

Use cases of mcp-code-guidance

Learning how to build a basic MCP server from scratch
Implementing a weather‑query MCP service (see mcp-server-02weather)
Building a stock‑price MCP service (see mcp-server-03stock)
Understanding how MCP tools, resources, and prompts work in practice
Exploring A2A agent‑to‑agent collaboration alongside MCP

Frequently asked questions

What are the required dependencies?

Python 3.10+ and the FastMCP library. The examples also use `httpx` and the `mcp` CLI package.

How do I set up the project environment?

Use the `uv` package manager: run `uv init` (specifying Python 3.11), `uv venv`, `source .venv/bin/activate`, then `uv add "mcp[cli]" httpx`.

What MCP capabilities are covered in this tutorial?

The tutorial covers all three MCP capabilities: Tool (direct function calls), Resource (context information), and Prompt (reusable templates).

Where does each example code live?

Each example is in its own directory under the repository root: `mcp-server-01quickstart`, `mcp-server-02weather`, `mcp-server-03stock`. A `tutorial/` directory contains detailed development guides.

What is the official MCP resource linked in the README?

The README links to https://modelcontextprotocol.io/introduction for the official MCP introduction.

Comments

More Developer Tools MCP servers

ArtiBot Cloud MCP - Zhijiangyun 智匠云

bofob

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Cronwatch

cronwatchdev

CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP