Krep MCP Server

@bmorphism

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

bmorphism

关于 Krep MCP Server

High-performance string search MCP server with automatic CPU core scaling

#krep#mcp#string-search#high-performance

Krep MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "krep": {
      "command": "node",
      "args": [
        "/path/to/krep-mcp-server/src/index.js"
      ],
      "env": {
        "CLAUDE_MCP": "true",
        "KREP_PATH": "/path/to/krep-native/krep",
        "DEBUG": "true"
      },
      "description": "High-performance string search utility with unified interface",
      "disabled": false,
      "autoApprove": [
        "krep"
      ]
    }
  }
}

Krep MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Krep MCP Server?

Krep MCP Server is a high‑performance string search utility that wraps the krep binary and exposes its functionality through the Model Context Protocol (MCP). It allows AI assistants to perform efficient pattern searching in files and strings using optimized algorithms and hardware acceleration.

How to use Krep MCP Server?

Install the krep binary, then configure the MCP server in your MCP settings file with the path to the server script and the required environment variables (e.g., KREP_PATH). Invoke the single unified function krep with parameters for pattern, target, mode, case sensitivity, and thread count.

Key features of Krep MCP Server

High‑performance search using KMP, Boyer‑Moore‑Horspool, and Rabin‑Karp algorithms
Hardware acceleration via SIMD instructions (SSE4.2/AVX2/NEON)
Optimized multi‑threading that auto‑detects all CPU cores
Unified interface: one function supporting file search, string search, and count‑only mode
Seamless integration with AI assistants through the Model Context Protocol
Automatic algorithm selection based on pattern length

Use cases of Krep MCP Server

AI assistants performing fast pattern matching in large codebases
Developers searching strings or files contextually within an IDE (e.g., Cline VSCode extension)
Counting occurrences of a pattern without retrieving full matches
Integrating with other MCP services (e.g., Babashka, Say, Coin‑Flip) in the infinity‑topos environment

常见问题

What is Krep MCP Server?

It is a wrapper around the krep binary that provides a high‑performance string search utility accessible through the Model Context Protocol, enabling AI assistants to search files and strings efficiently.

Does Krep MCP Server require the krep binary to be installed?

Yes. The server expects the krep binary to be present; its path can be specified via the `KREP_PATH` environment variable. The server will skip the check if `KREP_SKIP_CHECK` is set to `true`.

Can Krep MCP Server run in a non‑MCP mode?

Yes. When not running in MCP mode, the server starts an HTTP server with endpoints for health check, search, match, performance, and algorithm selection.

What search algorithms does Krep MCP Server use?

It uses Knuth‑Morris‑Pratt (KMP) for very short patterns (<3 characters), Boyer‑Moore‑Horspool for medium‑length patterns (3‑16 characters), and Rabin‑Karp for longer patterns (>16 characters). Hardware acceleration via SIMD is used when available.

How is Krep MCP Server integrated with Cline VSCode extension?

The server provides installation scripts (`install-cline-integration.sh`) and a test script (`run-cline-test.sh`) to set up the integration, allowing users to search with `/krep` commands directly in Cline conversations.

其他分类下的更多 MCP 服务器

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K