CodeMerge

CodeMerge

A Model Context Protocol server that uses Osmosis-Apply-1.7B to intelligently apply code edits while preserving the structure of the original code.

Category
访问服务器

README

CodeMerge

A Model Context Protocol (MCP) server that uses the Osmosis-Apply-1.7B model to merge code edits.

  • Code Merging: Uses the Osmosis/Osmosis-Apply-1.7B model to apply edits
  • MCP Integration: Works as a Model Context Protocol server to integrate into existing AI IDE solutions
  • File Operations: Can directly edit files in place or return edited code

Installation

Prerequisites

  • Python 3.10 or higher
  • Ollama installed and running
  • The Osmosis model pulled: ollama pull Osmosis/Osmosis-Apply-1.7B

Setup

  1. Clone the repository:
git clone <repository-url>
cd codemerge
  1. Install dependencies using uv:
uv sync
  1. Run:
uv run python codemerge.py

Usage

As an MCP Server

CodeMerge can be used as an MCP server. Configure it in your MCP client:

{
  "mcpServers": {
    "codemerge": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/codemerge",
        "run",
        "codemerge.py"
      ]
    }
  }
}

Direct Usage

You can also use CodeMerge directly in Python:

from call_snippet import apply_code_edit

# Original code
original_code = """def hello():
    print('Hello, World!')
    print('Some code')
    print('Some more code')
    return 'success'"""

# Edit to apply
edit_snippet = """def hello():
    print('Hello, Universe!')
    print('Some code')
    # ... existing code ...
    return 'success'"""

# Apply the edit
result = apply_code_edit(original_code, edit_snippet)
print(result)

MCP Tool Usage

The MCP server provides an edit_snippet tool with the following parameters:

  • original_code: The exact original code to be edited
  • edit_snippet: The edit to apply, using // ... existing code ... markers
  • file_path: Absolute path to a file to update in place

Example tool call:

{
  "name": "edit_snippet",
  "arguments": {
    "original_code": "def hello():\n    print('Hello, World!')",
    "edit_snippet": "def hello():\n    print('Hello, Universe!')\n    # ... existing code ...",
    "file_path": "/path/to/your/file.py"
  }
}

Edit Format

CodeMerge uses a specific format for edits that preserves context while being concise:

// ... existing code ...
FIRST_EDIT
// ... existing code ...
SECOND_EDIT
// ... existing code ...
THIRD_EDIT
// ... existing code ...

The // ... existing code ... markers indicate where the original code should be preserved. This allows you to specify only the parts you want to change while maintaining the exact structure and formatting of the original code.

Dependencies

  • httpx>=0.28.1: HTTP client for API calls
  • mcp[cli]>=1.10.1: Model Context Protocol implementation
  • ollama: Python client for Ollama (installed separately)

Architecture

CodeMerge consists of several components:

  • codemerge.py: Main MCP server implementation
  • call_snippet.py: Direct usage interface with streaming support
  • test_codemerge.py: Comprehensive test suite
  • pyproject.toml: Project configuration and dependencies

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选