Yanyue MCP acts as a digital bridge between AI assistants and the extensive cigarette database found on Yanyue.cn. In simple terms, it functions like a specialized librarian that allows an AI to look up specific information about different brands, types, and product details. By integrating this tool, users can ask an AI questions about various products and receive accurate, real-world data directly from a primary industry source. On a more technical level, the server provides a dedicated `searchCigarettes` tool that accepts keyword strings to query the database. It operates using the Model Context Protocol (MCP) over a standard input/output (`stdio`) transport layer, which ensures a secure and reliable communication channel between the AI client and the data retrieval logic. This allows a Large Language Model (LLM) to programmatically fetch and parse structured information to provide more informed responses. For developers looking to enhance their AI systems, this server is built for high performance using Node.js or Bun. It can be easily integrated into environments like Claude Desktop through a simple JSON configuration or automated via the Smithery CLI. By adding Yanyue MCP to their workflow, developers empower their AI applications with specialized domain knowledge that goes beyond static training data, enabling the model to access fresh, specific information during live conversations.
Category: CRM, ERP & E-commerce
Tags: consumer-goods, product-data, search, yanyue
bash npx -y @smithery/cli install @gandli/yanyue-mcp --client claude Manual Installation: 1. Clone the repository and install dependencies: bash git clone --depth 1 git@gandli:Yanyue-mcp/Yanyue-mcp.git cd Yanyue-mcp npm install # Or use Bun: bun install 2. Build the project: bash npm run build # Or use Bun: bun run buildconfig.json (e.g., Claude Desktop or Cursor configuration): json { "mcpServers": { "Yanyue_mcp": { "name": "Yanyue Cigarette Data", "description": "Fetch cigarette data from Yanyue", "type": "stdio", "command": "node", "args": ["path/to/build/index.js"] } } } Note: Replace path/to/build/index.js with the actual absolute path to the built file in your local installation.searchCigarettes(keyword: str): Search for cigarette information and data based on a specific keyword from Yanyue.cn.searchCigarettes to pull data for brands like "Chunghwa" or "Nanjing" and summarizes the feedback and price points.searchCigarettes tool, an AI can quickly pull the official technical data registered on Yanyue.cn. This provides a reliable "source of truth" for the physical characteristics of the product that would otherwise require manual searching through complex databases. Example: A user asks, "What is the tar and nicotine content of the 'Huanghelou (Soft Short 1916)'?" The AI calls the MCP, retrieves the exact specifications, and presents them clearly to the user for comparison with their product packaging.Part of MCP Servers
Yanyue MCP allows an AI assistant to query cigarette and tobacco information from Yanyue.cn. Through its search tool, the server retrieves technical specifications such as nicotine and tar ratings, suggested retail pricing, brand details, and user review scores. This helps users verify product authenticity, evaluate gift options, and perform consumer research directly from chat interactions.
Yanyue MCP connects to any client supporting the Model Context Protocol over a standard input and output transport layer. This includes desktop applications like Claude Desktop, developer environments like Cursor, and custom agent frameworks configured to run local command-line processes. Once registered in the client settings, the model gains access to the search tool automatically.
You can set up Yanyue MCP by cloning its repository from GitHub and building the project using Node.js or Bun. After compiling the source files, configure your MCP client by adding the server details to your settings file, specifying the node execution command and the path to the built entry script.
The server queries Yanyue.cn to fetch product listings, brand catalogs, manufacturing details, and physical specifications such as tar, nicotine, and carbon monoxide contents. It also provides pricing data and community feedback, allowing language models to answer specialized consumer inquiries with verified information from the primary source database.