Skip to main content
Glama
hwqlet

MCP Product Search Server

by hwqlet

MCP Product Search Server

A product search server based on the Model Context Protocol (MCP), allowing Claude to retrieve product catalogs based on keywords and return structured data.

Features

Provides three tools for Claude to call:

Tool

Description

search

Search for products by keyword, supports filtering by category, price, and rating

list_categories

List all product categories and their counts

get_product

Query full information for a single product by ID

Related MCP server: armls-spark-mcp-server

Quick Start

1. Clone the project

git clone <your-repo-url>
cd mcp-product-search

2. Create a virtual environment and install dependencies

macOS / Linux:

python3 -m venv .venv
source .venv/bin/activate
pip install "mcp[cli]"

Windows:

python -m venv .venv
.venv\Scripts\activate
pip install "mcp[cli]"

Requires Python 3.10 or higher. You can check with python3 --version.

3. Test in the browser

mcp dev server.py

The browser will automatically open the MCP Inspector. If it does not open automatically, manually visit the address output in the terminal (usually http://localhost:6274).

Connection Steps:

  1. Change the Command on the left to the absolute path of the Python executable in your virtual environment:

    • macOS/Linux: /absolute/path/to/mcp-product-search/.venv/bin/python

    • Windows: C:\absolute\path\to\mcp-product-search\.venv\Scripts\python.exe

  2. Fill in server.py for Arguments

  3. Click Connect. If the bottom left shows Connected, it is successful

  4. Click the Tools tab at the top, select a tool, fill in the parameters, and click Run Tool

MCP Inspector connection success illustration

4. Integrate with Claude Desktop

Locate the configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following content (replace with the actual absolute path):

{
  "mcpServers": {
    "product-search": {
      "command": "/绝对路径/mcp-product-search/.venv/bin/python",
      "args": ["/绝对路径/mcp-product-search/server.py"]
    }
  }
}

To view the absolute path of the current directory:

# macOS / Linux
pwd

# Windows
cd

After saving the configuration file, completely exit and restart Claude Desktop.

5. Integrate with Claude Code (CLI)

claude mcp add product-search \
  /绝对路径/mcp-product-search/.venv/bin/python \
  /绝对路径/mcp-product-search/server.py

Usage Examples

After connecting to Claude, you can ask questions like:

帮我搜索苹果品牌的笔记本电脑
找一款评分 4.8 以上、价格不超过 300 美元的耳机
列出所有产品分类
查询产品 P003 的详细信息

Claude will automatically determine which tool to call and provide an answer based on the returned structured data.

Tool Parameter Description

Parameter

Type

Required

Default

Description

keyword

string

Yes

Matches product name, description, brand, category, and tags

category

string

No

Filter by category, e.g., "Laptops", "Headphones"

max_price

float

No

Maximum price (USD)

min_rating

float

No

Minimum rating (0–5)

limit

int

No

10

Maximum number of results (up to 50)

Results are sorted by rating (descending) and price (ascending).

Return Example:

{
  "keyword": "apple",
  "filters": { "category": "Laptops", "max_price": null, "min_rating": null },
  "total_results": 1,
  "products": [
    {
      "id": "P001",
      "name": "Apple MacBook Pro 14-inch M3",
      "category": "Laptops",
      "brand": "Apple",
      "price": 1999.0,
      "currency": "USD",
      "stock": 42,
      "rating": 4.8,
      "description": "14-inch Liquid Retina XDR display, M3 chip, 18GB RAM, 512GB SSD.",
      "tags": ["laptop", "apple", "macbook", "m3", "professional", "portable"]
    }
  ]
}

list_categories

No parameters. Returns all category names and their corresponding product counts.

get_product

Parameter

Type

Required

Description

product_id

string

Yes

Product ID, e.g., "P001" (case-insensitive)

Project Structure

mcp-product-search/
├── server.py        # MCP 服务器,定义工具
├── products.py      # 产品目录与搜索逻辑
├── pyproject.toml   # 项目依赖
└── README.md

Extending Product Data

The current product catalog consists of 12 sample items written in products.py. To replace it with real data, simply modify the search_products() function; server.py does not need to be changed.

Data Source

How to modify

Local JSON/CSV

Read the file and populate CATALOG at startup

SQLite / PostgreSQL

Replace the traversal logic with SQL queries

E-commerce API

Send HTTP requests inside the function

Elasticsearch

Call the ES full-text search interface

Install Server
F
license - not found
A
quality
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    -
    quality
    C
    maintenance
    Enables users to search for products, retrieve details, and manage their shopping cart on Amazon through the MCP framework. It also supports viewing order history and provides a demonstration of ordering capabilities within AI interfaces.
    7
    42
    MIT
  • F
    license
    -
    quality
    C
    maintenance
    Enables Claude to query ARMLS Spark/FlexMLS real estate data including active listings, comparable sales, market statistics, and open houses via MCP tools.
  • F
    license
    -
    quality
    C
    maintenance
    Enables e-commerce operations such as product search, price updates, and order notes via MCP tools, with secure credential handling.
  • A
    license
    -
    quality
    D
    maintenance
    An MCP server that wraps the Universal Commerce Protocol (UCP) Discovery and Catalog capabilities, letting you search and compare products across UCP merchants directly from Claude.
    MIT

View all related MCP servers

Related MCP Connectors

  • Hosted Amazon Seller Central and Amazon Ads MCP server for Claude, ChatGPT, Cursor, and agents.

  • Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.

  • Shopping MCP for AI agents: search, compare, Amazon buy links. Auto-register.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hwqlet/mcp-product-search'

If you have feedback or need assistance with the MCP directory API, please join our Discord server