DIY MCP
A from-scratch implementation of the Model Context Protocol (MCP) for building servers and clients, using a Chinese tea collection as an example.
DIY MCP
A simple from-scratch implementation of the Model Context Protocol (MCP) for building MCP servers and clients using stdio. This example uses a simple Chinese tea collection with descriptions, origins, etc.
For production applications, check out the official MCP SDKs.
Project Structure
mcp/
├── server/ # MCP server for Chinese tea information
│ └── src/
│ ├── index.ts
│ ├── stdio.ts
│ └── teas.json
└── client/ # MCP client CLI with Claude as LLM
└── src/
├── index.ts
└── llm.ts
MCP Server
The core of this implementation is a lightweight MCP server. It offers the following resources and tools:
- Resources:
tea://teas: List of all available teastea://teas/{slug}: Details of a specific tea
- Tools:
getTeasByType: Get all teas of a specific typegetTeasByRegion: Get all teas from a specific province or region
Setup
cd server
npm install
npm run build
Running
You can test the MCP server with MCP Inspector, an interactive tool for testing and debugging MCP servers.
cd server
npm run inspector
MCP Client
You can interact with the MCP server through an MCP client like Claude Desktop, alternatively, you can use the included DIY MCP client. By adding your Anthropic API key, you can have Claude intelligently determine which tools to use based on your prompt.
The client provides three interaction modes:
- Ask LLM: Let Claude interact with the MCP server
- Get a resource: Directly access MCP server resources
- Use a tool: Directly call MCP server tools
Setup
cd client
npm install
To use Claude, first copy the example environment file and add your Anthropic API key with available credits to the ANTHROPIC_API_KEY variable:
cp .env.example .env
Running
The client will automatically start the MCP server, so ensure you've built it first.
cd server
npm run build
cd client
npm start
Usage
Once running, you can interact with the MCP server through the MCP client CLI. Try asking the LLM some questions about Chinese tea:
- "What teas do you know about?"
- "Which teas come from Fujian?"
- "What is your favorite green tea?"
Resources
Related Servers
Loki MCP Server
A Go-based server to query Grafana Loki logs using the Model Context Protocol (MCP).
MCP Framework Starter
A starter project for building Model Context Protocol (MCP) servers with the mcp-framework.
MCP API Bridge
A server that bridges Google Sheets, Azure AI, and MQTT APIs.
Multichain MCP Server
A toolkit for building and deploying AI agents with blockchain capabilities, featuring a Model Context Protocol (MCP) server.
Agent Engineering Bootcamp MCP
A server providing setup guidance for students learning agent development, with support for both Python and TypeScript.
Gentoro
Gentoro generates MCP Servers based on OpenAPI specifications.
MCP Gateway
Integrates multiple MCP servers into a single interface with a management Web UI and real-time status updates.
Whistle MCP Server
Manage local Whistle proxy servers through AI assistants, simplifying network debugging, API testing, and rule management.
MCP Prompt Collector
Tools for logging, analyzing, and improving Claude Desktop prompts to enhance prompt engineering skills.
GitLab MR & Confluence Linker
Analyzes GitLab merge requests and links them to Confluence documentation.