Phonelcdparts Mcp

by cnguyen14

327 downloads
Not rated
GitHub

About

Phoneldparts Mcp is a Model Context Protocol server that scrapes product search results from phonelcdparts.com using Firecrawl and BeautifulSoup. It provides a tool for programmatically retrieving product name, price, URL, and image URL for any search query. It is intended for…

Details

Author
cnguyen14
Downloads
327
Categories
Other

- Exposes the scrape_phonelcdparts MCP tool for product search.
- Open source under the MIT License.
- Ready for hosting on MCP.so via chatmcp.yaml.
- Uses Firecrawl for web scraping with a simple API key setup.
- Returns product name, price, URL, and image URL per result.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Phonelcdparts Mcp
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Python 3.12+, set the FIRECRAWL_API_KEY environment variable, then either run python app.py or use the start-mcp script. The server exposes a single MCP tool named scrape_phonelcdparts that accepts a search_query string argument.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "phonelcdparts mcp": {
            "PhoneLCDPartsScraper": {
                "command": "fastmcp",
                "args": [
                    "run",
                    "app.py"
                ],
                "env": {
                    "FIRECRAWL_API_KEY": "{FIRECRAWL_API_KEY}"
                }
            }
        }
    }
}

McpServers

{
    "PhoneLCDPartsScraper": {
        "command": "fastmcp",
        "args": [
            "run",
            "app.py"
        ],
        "env": {
            "FIRECRAWL_API_KEY": "{FIRECRAWL_API_KEY}"
        }
    }
}
# PhoneLCDParts MCP Server A Model Context Protocol (MCP) server for scraping product search results from [phonelcdparts.com](https://www.phonelcdparts.com) using Firecrawl and BeautifulSoup. This server exposes a tool for programmatically retrieving product information (name, price, URL, image) for any search query. ## Features - **MCP Tool:** `scrape_phonelcdparts` — Scrape product listings for any search term. - **Open Source:** MIT License. - **Ready for MCP.so Hosting:** Includes `chatmcp.yaml` and environment variable support. ## Requirements - Python 3.12+ - [Firecrawl API Key](https://firecrawl.dev/) ## Installation Clone the repository and install dependencies (recommended: use a virtual environment): ```bash uv venv .venv source .venv/bin/activate uv pip install . ``` ## Usage (Local) Set your Firecrawl API key and run the server: ```bash export FIRECRAWL_API_KEY=your_firecrawl_api_key python app.py ``` Or use the provided script (if installed): ```bash start-mcp ``` ## MCP Tool ### scrape_phonelcdparts **Arguments:** - `search_query` (str): The product search query (e.g., "iphone 15 pro max lcd") **Returns:** - List of products, each with: - `name`: Product name - `price`: Price string - `url`: Product page URL - `image_url`: Product image URL ## Environment Variables - `FIRECRAWL_API_KEY` (required): Your Firecrawl API key for web scraping. ## MCP.so Hosting This project is ready for [MCP.so](https://docs.mcp.so/server-hosting) hosting: - Includes `chatmcp.yaml` for parameter and run command specification. - Reads API key from environment variable. - MIT License included. ### To Host: 1. Push your code to a public GitHub repository. 2. Submit your repo to MCP.so for review and hosting. ## License This project is licensed under the MIT License. See [LICENSE](LICENSE) for details.
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.