Krep MCP Server

🚀 Krep MCP Server

Krep MCP Server is a powerful string search tool that supports file and string pattern matching and provides services through the Model Context Protocol (MCP) interface. It is suitable for various scenarios requiring high-performance string search.

🚀 Quick Start

Krep MCP Server offers a high - performance solution for string search. It can be easily integrated into different environments and used for various search tasks.

✨ Features

• Unified Interface: Achieve file and string search as well as counting functions through a single function.
• Multithreading Support: Automatically utilize all CPU cores to enhance performance.
• Hardware Acceleration: Optimize search speed using SIMD instructions.
• Intelligent Algorithm Selection: Automatically select the best algorithm based on the pattern length:
  • KMP algorithm (for patterns shorter than 3 characters).
  • Boyer - Moore - Horspool algorithm (for patterns between 3 - 16 characters).
  • Rabin - Karp algorithm (for patterns longer than 16 characters).

📦 Installation

Installation in MCP Mode

To integrate the Krep MCP Server with Infinity Topos, follow these steps:

Download and Installation

# Clone the repository
git clone https://github.com/your-repository/krep-mcp-server.git
cd krep-mcp-server

# Install dependencies
npm install

# Start the server
node src/index.js

💻 Usage Examples

Example of Using MCP Mode

<use_mcp_tool>
  <server_name>krep</server_name>
  <tool_name>krep</tool_name>
  <arguments>
    {
      "pattern": "Search pattern",
      "target": "File path or string",
      "mode": "file|string|count",
      "caseSensitive": true|false,
      "threads": null // Automatically detect the number of CPU cores, default is all cores
    }
  </arguments>
</use_mcp_tool>

Parameters

• pattern (Required): The pattern to search for.
• target (Required): The file path or the string to search in.
• mode (Optional): Search mode.
  • file (Default): Search in a file.
  • string: Search in a string.
  • count: Only count the number of occurrences.
• caseSensitive (Optional): Whether to be case - sensitive (Default: true).
• threads (Optional): The number of threads to use (Default: automatically detect the number of CPU cores).

📚 Documentation

How It Works

The Krep MCP Server processes requests through the following steps:

1. Receive a request from the Model Context Protocol.
2. Parse the request parameters.
3. Build an appropriate krep command based on the pattern and parameters.
4. Execute the krep binary file.
5. Parse the results and return them in a structured format.

Performance

Krep is designed for high - performance pattern search:

• Algorithm Selection: Automatically select the optimal algorithm based on the pattern length.
  • KMP (Knuth - Morris - Pratt) is suitable for very short patterns (< 3 characters).
  • Boyer - Moore - Horspool is suitable for medium - length patterns (3 - 16 characters).
  • Rabin - Karp is suitable for longer patterns (> 16 characters).
• Hardware Acceleration: Optimize performance using SIMD instructions.
• Dynamic Multithreading: Automatically utilize all available CPU cores for optimal parallel search performance.

Integration with Cline VSCode Extension

The Krep MCP Server can be integrated with the Cline VSCode extension to use high - performance string search functions directly in the VSCode environment.

Installation with Cline

We provide an automatic installation script to set up the Cline integration:

# Install the integration
./install-cline-integration.sh

# Test before installation
./run-cline-test.sh

# Uninstall the integration
./uninstall-cline-integration.sh

Using Krep in Cline

Once integrated, you can directly use krep in Cline conversations.