Power your agent
Cài đặt từ nhà phát hành. Không phải endpoint của PlugMCP.
Host a copy with our keys and logs.
Chưa có bản phát hành đóng gói nào trong registry. Làm theo README của kho mã.
URL từ xa hay một lệnh trên máy của bạn? Hai cách cài đặt khác nhau thế nào
Chạy trên PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
MởTừ nhà phát hành
A hands-on bootcamp to master the Model Context Protocol (MCP) — from building your first server to deploying production-ready AI agents. Covers 16 real-world projects using Claude, Gemini, LangChain, Docker, SSE, and more.
A hands-on, project-based bootcamp covering everything you need to master the Model Context Protocol — from fundamentals to full-stack production-ready AI agents.
Model Context Protocol (MCP) is an open standard introduced by Anthropic that defines how AI models communicate with external tools, data sources, and services. Think of it as the "USB standard for AI" — it provides a universal plug-and-play interface that lets any LLM connect to any tool or data source without custom integrations.
This bootcamp is structured as 16 progressive modules, each building on the last — from core concepts to production-ready, multi-agent systems.
Foundation | Conceptual Overview
Understand the architecture of MCP from the ground up. This module covers:
📄 Includes a comprehensive PDF reference guide.
Beginner | Python · FastMCP · Claude Desktop
Build your first real MCP server and connect it directly to Claude Desktop. This module walks through:
FastMCPclaude_desktop_config.json for local MCP server registration# Your first MCP tool
@mcp.tool()
async def run_command(command: str) -> str:
"""Run a terminal command inside the workspace directory."""
...
📁 terminal_server/ · claude_desktop_config.json
Beginner | Python · FastMCP · Cursor IDE
Connect your MCP server to Cursor IDE and supercharge your coding workflow:
📁 terminal_server/src/
Intermediate | Python · Google Gemini API · Custom MCP Client
Move beyond Claude Desktop — build a fully custom MCP client powered by the Google Gemini API:
📁 mcp-client/client.py
Intermediate | Docker · Python · Containerization
Package and deploy your MCP server as a Docker container for portability and reproducibility:
Dockerfile for an MCP server# Containerized MCP server
FROM python:3.11-slim
COPY . /app
RUN pip install -r requirements.txt
CMD ["python", "terminal_server.py"]
📁 terminal_server/ · Dockerfile · claude_desktop_config.json
Intermediate | LangChain · Python · MCP Adapters
Integrate MCP tools into the LangChain ecosystem using official MCP adapters:
langchain-mcp-adapters to wrap MCP tools as LangChain toolsfrom langchain_mcp_adapters.tools import load_mcp_tools
tools = await load_mcp_tools(session)
agent = create_react_agent(model, tools)
📁 mcp-clients/lanchain_mcp_client.py
Intermediate | Python · LangChain · Multi-Server Architecture
Scale your MCP setup by connecting a single client to multiple servers:
config.json file{
"servers": {
"terminal": { "command": "python", "args": ["server.py"] },
"weather": { "command": "python", "args": ["weather_server.py"] }
}
}
📁 mcp-client/langchain_mcp_client_wconfig.py · config.json
Intermediate | Python · SSE Transport · HTTP
Switch from stdio to Server-Sent Events (SSE) transport for network-based MCP communication:
📁 servers/terminal_server/sse_server/ · clients/mcp_client/
Intermediate | Python · FastMCP · External APIs · MCP Inspector
Build a production-style real-time weather agent and debug it with the official MCP Inspector tool:
tools/ package@mcp.tool()
async def get_weather(city: str) -> dict:
"""Fetch real-time weather data for a given city."""
...
📁 tools/weather.py · main.py
Advanced | Python · FastMCP · LangChain · Streamlit · Job APIs
A full-stack AI-powered job recommendation agent built on MCP:
mcp_server.py) and agent logic (app.py)📁 app.py · mcp_server.py · src/job_api.py · src/helper.py
Advanced | Python · FastMCP · LangChain · Streamlit · Generative AI
An end-to-end AI creative writing agent that generates rich, structured stories:
📁 app.py · mcp_server.py · main.py
Advanced | Python · FastMCP · PubMed API · LangChain · Medical NLP
A specialized clinical intelligence agent for medical research and symptom analysis:
Tools: symptom_extractor · pubmed_search · summarize_article · differential_diagnosis
📁 functions/ · mcp_tool.py · app.py · demo.ipynb
Advanced | Google ADK · Multi-Agent Systems
Explore Google's Agent Development Kit (ADK) for orchestrating multiple specialized agents:
📁 muli_agent/agent.py
Advanced | Python · Flask · LangChain · Flight APIs · Tavily Search
A full-stack AI travel planning assistant with a beautiful web interface:
📁 app.py · backend.py · tools/ · templates/ · static/ · Dockerfile
Advanced | Python · MCP · Flask · Custom Weather MCP Server
The MCP-powered evolution of TripMate-AI — refactored to use MCP as the tool integration layer:
custom_weather_mcp_server.py)Architecture: Browser → Flask App → MCP Client → [Weather MCP Server, Flight Tools, Search Tools]
📁 mcp_client.py · custom_weather_mcp_server.py · backend.py · Dockerfile
Advanced | Python · LangChain · Google Gemini · DALL-E · Flask
A sophisticated AI blog writing agent with image generation capabilities:
Pipeline: Topic → Research → Outline → Draft → Image Generation → Final Blog Post
📁 app.py · backend.py · notebooks/ · static/ · templates/
Make sure you have the following installed:
uv (recommended) or pipgit clone https://github.com/Suraj-G-Rao/Complete-Model-Context-Protocol-MCP-.git
cd Complete-Model-Context-Protocol-MCP-
Each module is self-contained. Navigate to any folder and follow these steps:
Using uv (recommended):
cd "04-Build Your Own MCP Client using Google Gemini API/mcp-client"
uv sync
cp .env.example .env # Add your API keys
uv run python client.py
Using pip:
cd "04-Build Your Own MCP Client using Google Gemini API/mcp-client"
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
cp .env.example .env # Add your API keys
python client.py
Each project that requires API keys includes a .env.example file. Common variables:
GOOGLE_API_KEY=your_google_gemini_api_key
ANTHROPIC_API_KEY=your_anthropic_api_key
OPENAI_API_KEY=your_openai_api_key
TAVILY_API_KEY=your_tavily_api_key
OPENWEATHER_API_KEY=your_openweather_api_key
Complete-Model-Context-Protocol-MCP-/
│
├── 01-Introduction to MCP/ # 📖 MCP concepts & PDF guide
├── 02-Build MCP Server with Claude Desktop/ # 🖥️ First MCP server + Claude Desktop
├── 03-Cursor IDE MCP Server Setup/ # 🖱️ MCP in Cursor IDE
├── 04-Build Your Own MCP Client.../ # 💎 Custom Gemini-powered MCP client
├── 05-How to build Docker MCP Server/ # 🐳 Dockerized MCP server
├── 06-Langchain MCP Client.../ # 🦜 LangChain + MCP adapters
├── 07-MCP Client with Multiple Server.../# 🔗 Multi-server MCP client
├── 08-MCP Server and Client using SSE/ # 📡 SSE transport layer
├── 09-Real Time Weather Agent.../ # 🌦️ Weather agent + MCP Inspector
├── 10-Real Time Job Recommendation.../ # 💼 Full-stack job recommender
├── 11-StoryForge Agent/ # 📖 AI creative writing agent
├── 12-Clinisight/ # 🏥 Clinical AI assistant
├── 13-ADK demo/ # 🤖 Google ADK multi-agent
├── 14-TripMate-AI/ # ✈️ Travel planner web app
├── 15-TripMate-AI Using MCP/ # ✈️🔌 MCP-powered travel planner
├── 16-AgentWriter-AI/ # ✍️ AI blog writing agent
│
├── .gitignore
└── README.md
Beginner ─────────────────────────────────────────────────────► Advanced
│ │
[01] [02] [03] [04] [05] [06] [07] [08] │
Concepts First Server Custom Client LangChain & Docker │
│ │ │ │
[09] [10] [11] [12] [13] [14][15][16]
Weather Agent Job Rec. Full-Stack Agents Production Apps
Contributions are welcome! If you find a bug, want to improve documentation, or add a new module:
git checkout -b feature/your-featuregit commit -m "Add your feature"git push origin feature/your-featureThis project is licensed under the MIT License — see the LICENSE file for details.
Built with ❤️ to help developers master the future of AI tool integration
A hands-on bootcamp to master the Model Context Protocol (MCP) — from building your first server to deploying production-ready AI agents. Covers 16 real-world projects using Claude, Gemini, LangChain,
Tổng quan
A hands-on bootcamp to master the Model Context Protocol (MCP) — from building your first server to deploying production-ready AI agents. Covers 16 real-world projects using Claude, Gemini, LangChain, Docker, SSE, and more.
Công cụ
Chưa có danh sách công cụ. Máy chủ từ xa sẽ có danh sách sau lần kiểm tra tình trạng đầu tiên.
Câu hỏi thường gặp
Sao chép cấu hình stdio cho Cursor, Claude Desktop, Claude Code hoặc VS Code trên trang này. Cấu hình dùng bản cài đặt của nhà phát hành, không phải proxy của PlugMCP.
Bản ghi này không liệt kê biến môi trường bắt buộc nào.
Complete Model Context Protocol Bootcamp chạy cục bộ qua stdio.
Kiểm tra lần cuối: 2026-10-28. A hands-on bootcamp to master the Model Context Protocol (MCP) — from building your first server to deploying production-ready AI agents. Covers 16 real-world projects using Claude, Gemini, LangChain, Docker, SSE, and more.