Book Fetch (Library Genesis) MCP server

This tool provides direct interaction with published books right within Claude or other MCP clients. It allows you to query books and receive responses, complete with features like pagination for lengthy texts and an integrated RAG engine to enhance your interactions with book content.

Installation

Prerequisites

• Make sure you have uv (Python package manager) installed on your system
• Clone or download the book-fetch MCP repository

Setup Steps

1. Navigate to the book-fetch directory:

   cd book-fetch
   

2. Install dependencies using uv:

   uv pip install -r requirements.txt
   

3. Configure Claude Desktop to work with the book-fetch MCP by adding the following to your claude_desktop_config.json file:

   {
     "mcpServers": {
       "book-fetcher": {
           "command": "uv",
           "args": [
           "--directory",
           "<PATH_TO_PARENT_DIR>/libgen-mcp",
           "run",
           "main.py"
           ]
       }
     }
   }
   

   Be sure to replace <PATH_TO_PARENT_DIR> with the actual path to the parent directory containing the libgen-mcp folder.

Usage

Basic Book Interaction

Once configured, you can interact with books directly within Claude by invoking the book-fetch MCP service. The tool will:

• Fetch book content based on your queries
• Handle pagination automatically for lengthy books
• Maintain books in the MCP cache for improved performance

Advanced Features

The book-fetch MCP includes:

• Integrated RAG Engine: Efficiently processes book content with automatic ingestion, chunking, and reranking
• Long-Context Support: Uses Gemini 1.5 for processing lengthy book content
• SciHub Integration: Access to academic papers and research

Using with Claude

Simply ask Claude to use the book-fetcher to find or reference information from a specific book. For example:

• "Use book-fetcher to find information about quantum physics in 'A Brief History of Time'"
• "Ask book-fetcher to summarize Chapter 3 of 'Pride and Prejudice'"

The service will automatically handle the retrieval, processing, and presentation of relevant content from the requested book.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.