MCP Chinese Getting Started
Model Context Protocol(MCP) 编程极速入门
What is MCP Chinese Getting Started?
MCP Chinese Getting Started is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol(mcp) 编程极速入门
Model Context Protocol(MCP) 编程极速入门
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Protocol(MCP) 编程极速入门
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-chinese-getting-started-guideConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Chinese Getting Started
MCP Chinese Getting Started Guide is a hands-on tutorial repository that teaches developers how to build Model Context Protocol servers from scratch using Python, with all explanations in Chinese. It walks through creating real-world example servers — including a web search server using Zhipu's API, a file management server with human-in-the-loop confirmation, an image generation server via Hugging Face's FLUX model, and a prompt/resource template server — progressing from local stdio transports to cloud deployment on Alibaba's serverless platform. Developers new to MCP who prefer Chinese-language documentation use it as an accelerated on-ramp to building production MCP tools.
Prerequisites
- Python 3.10+ installed
- uv package manager installed (recommended) or pip
- A Zhipu AI API key (for the web search example server) — register at open.bigmodel.cn
- An MCP client such as Claude Desktop for testing the servers you build
- Optional: Hugging Face account and API token for the image generation example
Create a new project with uv
Initialize a new Python project using uv, which handles virtual environment creation and dependency management in one step.
uv init mcp_getting_started
cd mcp_getting_started
uv venvActivate the virtual environment
Activate the virtual environment before installing dependencies. The command differs slightly between Windows and Unix systems.
# Windows:
.venv\Scripts\activate.bat
# macOS/Linux:
source .venv/bin/activateInstall MCP and required dependencies
Install the MCP Python SDK with CLI support, plus httpx for HTTP requests and openai for compatibility with Zhipu's OpenAI-compatible API.
uv add "mcp[cli]" httpx openaiCreate a minimal MCP server
Use FastMCP to define a tool with a decorator. This pattern is the foundation for all example servers in the guide.
from mcp.server import FastMCP
app = FastMCP('my-service')
@app.tool()
async def my_tool(query: str) -> str:
"""Describe what this tool does."""
return f"Result for: {query}"
if __name__ == '__main__':
app.run()Test your server with MCP Inspector
Use the MCP Inspector to interactively test your server's tools before connecting it to Claude Desktop. This lets you call tools directly and see their output.
npx -y @modelcontextprotocol/inspector uv run my_server.py
# Or using mcp dev shortcut:
mcp dev my_server.pyRegister the server with Claude Desktop
Add your custom server to Claude Desktop's configuration so you can test it with a real AI client.
{
"mcpServers": {
"my-mcp-server": {
"command": "uv",
"args": ["run", "/absolute/path/to/my_server.py"]
}
}
}MCP Chinese Getting Started Examples
Client configuration
Claude Desktop configuration for a locally developed MCP server built following the guide.
{
"mcpServers": {
"web-search-server": {
"command": "uv",
"args": ["run", "/path/to/mcp_getting_started/web_search.py"],
"env": {
"ZHIPU_API_KEY": "your-zhipu-api-key-here"
}
}
}
}Prompts to try
Example prompts to test the example servers built following the guide.
- "Search the web for the latest news about Model Context Protocol"
- "Generate an image of a sunset over mountains using the image generation tool"
- "Delete the file /tmp/test.txt — confirm the action before proceeding"
- "Use the web search tool to find the top 5 Python MCP libraries available today"
- "Show me the available prompt templates in this MCP server"Troubleshooting MCP Chinese Getting Started
uv command not found
Install uv with: curl -LsSf https://astral.sh/uv/install.sh | sh (macOS/Linux) or irm https://astral.sh/uv/install.ps1 | iex (Windows PowerShell). Restart your terminal after installation.
Zhipu API returns authentication errors
Ensure your ZHIPU_API_KEY is set correctly as an environment variable. Keys are found in your Zhipu AI console at open.bigmodel.cn. The guide uses the OpenAI-compatible endpoint, so also verify the base_url is set to https://open.bigmodel.cn/api/paas/v4/.
MCP Inspector shows no tools when testing the server
Ensure your Python file defines at least one function decorated with @app.tool() and that the file runs without errors when executed directly with 'uv run my_server.py'. Check for import errors or missing dependencies.
Frequently Asked Questions about MCP Chinese Getting Started
What is MCP Chinese Getting Started?
MCP Chinese Getting Started is a Model Context Protocol (MCP) server that model context protocol(mcp) 编程极速入门 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Chinese Getting Started?
Follow the installation instructions on the MCP Chinese Getting Started GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Chinese Getting Started?
MCP Chinese Getting Started works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Chinese Getting Started free to use?
Yes, MCP Chinese Getting Started is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP Chinese Getting Started Alternatives — Similar Developer Tools Servers
Looking for alternatives to MCP Chinese Getting Started? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Chinese Getting Started in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Chinese Getting Started?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.