HarmonyOS MCP 서버

                                                                                                                               

소개

이것은 조화OS Device를 조작하기위한 MCP 서버입니다.

https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17] [T0]] [T0]] [T0]] [T0]] [T0]] [T0]] [T0]] [T0] [T0] [T0]] [T0] [T0] [T0]] [T0]] [T0] [T0] [T0] [T0] [T0]] [T0] [T0]] [T0] [T0] [T0]] [T0]] [T0] [T0] [T0]] https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17] https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17]]] https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17]]]]]] [[https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17]]]]]]] [[[[[[https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17]]]]]]]]]]]]]] [[[[[[[https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17]]]]]]]]]]]]]]]]]] [[[[[[[[[[[[[[[[[[[[[[

빠른 시작

설치

1. 이 repo를 복제

2. 환경 설정.

사용법

###1.Claude 데스크탑

Claude Desktop을 사용하여 도구를 시도 할 수 있습니다.

###2.Openai SDK를 openai-agents SDK를 사용하여 mcp 서버를 시도할 수 있습니다. 여기에 예

# # # # 3.Langchain의

LLM Agent Framework를 사용하여 작업 흐름을 설계할 수 있습니다. 여기에 예

server.py에서 시스템 프롬프트 작성

load_mcp_prompt] 함수를 사용하여 mcp 서버에서 프롬프트를 얻을 수 있습니다.

Intro

This is a MCP server for manipulating harmonyOS Device.

https://github.com/user-attachments/assets/7af7f5af-e8c6-4845-8d92-cd0ab30bfe17

Quick Start

Installation

1. Clone this repo

git clone https://github.com/XixianLiang/HarmonyOS-mcp-server.git
cd HarmonyOS-mcp-server

2. Setup the envirnment.

uv python install 3.13
uv sync

Usage

1.Claude Desktop

You can use Claude Desktop to try our tool.

2.Openai SDK

You can also use openai-agents SDK to try the mcp server. Here’s an example

"""
Example: Use Openai-agents SDK to call HarmonyOS-mcp-server
"""
import asyncio
import os

from agents import Agent, Runner, gen_trace_id, trace
from agents.mcp import MCPServerStdio, MCPServer

async def run(mcp_server: MCPServer):
    agent = Agent(
        name="Assistant",
        instructions="Use the tools to manipulate the HarmonyOS device and finish the task.",
        mcp_servers=[mcp_server],
    )

    message = "Launch the app `settings` on the phone"
    print(f"Running: {message}")
    result = await Runner.run(starting_agent=agent, input=message)
    print(result.final_output)

async def main():

    # Use async context manager to initialize the server
    async with MCPServerStdio(
        params={
            "command": "/bin/uv",
            "args": [
                "--directory",
                "/harmonyos-mcp-server",
                "run",
                "server.py"
            ]
        }
    ) as server:
        trace_id = gen_trace_id()
        with trace(workflow_name="MCP HarmonyOS", trace_id=trace_id):
            print(f"View trace: https://platform.openai.com/traces/trace?trace_id={trace_id}\n")
            await run(server)

if __name__ == "__main__":
    asyncio.run(main())

3.Langchain

You can use LangGraph, a flexible LLM agent framework to design your workflows. Here’s an example

"""
langgraph_mcp.py
"""

server_params = StdioServerParameters(
    command="/home/chad/.local/bin/uv",
    args=["--directory",
          ".",
          "run",
          "server.py"],
    
)

#This fucntion would use langgraph to build your own agent workflow
async def create_graph(session):
    llm = ChatOllama(model="qwen2.5:7b", temperature=0)
    #!!!load_mcp_tools is a langchain package function that integrates the mcp into langchain.