mcpField
B
Bazos MCP Server

Bazos MCP Server

Local
github.com/progresakSearch0Updated 76w ago

About Bazos MCP Server

Bazos MCP Server lets MCP-compatible assistants search current graphics card listings on Bazos.cz. It scrapes listing details and returns them as structured results.

Key features

  1. 01Search graphics card listings
  2. 02Filter by a query
  3. 03Return price, location, and description
  4. 04Include listing and image URLs

Use cases

  1. 01Find listings for a specific GPU model
  2. 02Review prices and locations for available cards

MCP support

It exposes the `search-graphics-cards` tool to MCP clients, accepting a required search query and returning scraped listing data.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Bazos MCP Server

A Model Context Protocol (MCP) server that provides real-time graphics card listings from Bazos.cz marketplace. This server enables AI assistants to search and retrieve current graphics card listings through a standardized interface.

Features

  • Real-time scraping of graphics card listings from pc.bazos.cz/graficka/
  • Returns structured data including:
    • Title
    • Price
    • Location
    • URL
    • Image URL
    • Description
  • Integration with Claude and other MCP-compatible AI assistants
  • Clean TypeScript implementation
  • Implemented using @modelcontextprotocol/sdk

Installation

# Clone the repository
git clone https://github.com/progresak/bazos-mcp-server.git

# Install dependencies
npm install

Usage

Build and start the MCP server:

# Build the TypeScript code
npm run build

# Start the server
npm start

For development with automatic recompilation:

npm run dev
Integration with Claude and other AI Assistants

This server can be used with any MCP-compatible LLM interface, including Claude Desktop. The server provides the following tool:

  • search-graphics-cards: Search for real graphics card listings on Bazos.cz
    • Parameters:
      • query (required): Filter listings by this search term (e.g., "RTX 4090", "RTX 4070")
MCP Server Configuration

Add this server to your MCP configuration:

{
  "mcpServers": {
    "bazos": {
      "command": "node",
      "args": ["/path-to-this-repository/bazos-mcp-server/dist/index.js"]
    }
  }
}

Implementation Details

The server works by:

  1. Receiving a search query via the MCP interface
  2. Constructing the appropriate Bazos.cz search URL
  3. Scraping the HTML using cheerio
  4. Parsing listing information (title, price, location, URLs)
  5. Returning structured data to the client

Project Structure

  • src/index.ts - Main MCP server implementation
  • src/bazos.ts - Scraping functionality for Bazos.cz

Dependencies

  • @modelcontextprotocol/sdk: For MCP server implementation
  • cheerio: For HTML parsing and data extraction

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see the LICENSE file for details

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.