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
TestRail
Interact with TestRail's core entities such as test cases, runs, and results using a standardized protocol.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
MCP Low-Level Server Streamable HTTP
A low-level MCP server implementation with streamable HTTP support, configured via environment variables.
MAVAE - IMAGE TOOLBOX
A creative toolkit for AI agents to generate, edit, and manage images, models, and collections using the MAVAE API.
CircleCI
Enable AI Agents to fix build failures from CircleCI.
Cloudflare MCP Server
An example MCP server designed for easy deployment on Cloudflare Workers, operating without authentication.
MCP Command Server
A server for securely executing commands on the host system, requiring Java 21 or higher.
Symbolic Algebra MCP Server
Perform symbolic mathematics and computer algebra using the SymPy library.
DINO-X
Advanced computer vision and object detection MCP server powered by Dino-X, enabling AI agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks.
Remote MCP Server on Cloudflare
A template for deploying a remote MCP server on Cloudflare Workers, customizable by defining tools in the source code.