mcp-servers
openEuler MCP Servers
Documentation
openEuler MCP Servers仓库,欢迎大家贡献
[pypi-badge]: https://img.shields.io/pypi/v/mcp.svg
[pypi-url]: https://pypi.org/project/mcp/
[python-badge]: https://img.shields.io/pypi/pyversions/mcp.svg
[python-url]: https://www.python.org/downloads/
[docs-badge]: https://img.shields.io/badge/docs-modelcontextprotocol.io-blue.svg
[docs-url]: https://modelcontextprotocol.io
[spec-badge]: https://img.shields.io/badge/spec-spec.modelcontextprotocol.io-blue.svg
[spec-url]: https://spec.modelcontextprotocol.io
介绍
MCP是Model Context Protocol的缩写,旨在提供一个通用的大模型上下文协议,用来调用各种应用,拓展大模型能力,openEuler的mcp-servers仓库用来存放各种MCP Server,聚焦于操作系统领域,结合Devstation,EulerCopilot改善openEuler交互体验
软件架构
仓库目录带一个doc目录,用来存放整体的各类文档介绍,之后servers每个文件夹为一个独立的MCP Server
mcp-servers/
├── servers
│ ├── oeDeploys/
│ │ ├── mcp_config.json
│ │ ├── mcp-rpm.yaml
│ │ └── src/
│ │ ├── icon.png
│ │ ├── mcp-oedp.py
│ │ ├── readme.md
│ │ └── requirements.txt
│ ├── oeGitExt/
│ └── xxxxx/
├── scripts/
└── doc/以oeDeploy为例,每个server顶层需要包含以下几个内容:
1、MCP配置文件 - 包含MCP Server的配置信息
2、部署配置文件 - 包含其他相关配置文件
3、源码目录 - 包含MCP Server的具体实现代码和相关资源文件
其中doc中的 MCP描述文档 给出了 MCP Servers 的描述建议,用于提升MCP Servers的易用性
使用说明
1、使用常用的MCP客户端完成配置如EulerCopilot,Roo Code,Cline等等
2、将MCP Server的配置文件写入到MCP客户端
使用yum自动安装(推荐):
openEuler社区会将每个MCP Server构建为一个个RPM包,用户直接yum install安装即可使用,即将上线
快速开始:如何使用MCP Python-SDK编写一个自己的MCP Server服务器
MCP环境搭建
1、安装 `uv` Python管理工具
yum install -y uv2、安装MCP
yum install -y python3-mcp实战编码
1、挑选一个小工具oegitext
oegitext是一个用来和gitee交互的小工具,可以用来查询在gitee上面的一些仓库和issue,查询一些PR信息:
该工具在DevStation上预安装,如果没有安装,可以在配置openEuler-25.03 EPOL仓库后使用 `yum install oegitext安装`
安装完成之后,使用如下命令配置gitee令牌:
oegitext config -token ${access_token}之后使用`oegitext show issue -p`查询当前issue:

2、使用python-sdk进行一个改造
在上面使用uv创建的虚拟环境中,新建一个oegitext_mcp.py文件
下面是代码的一个简单示例:
import subprocess
from mcp.server.fastmcp import FastMCP
mcp = FastMCP("查找openEuler社区的issue")
@mcp.tool()
def get_my_openeuler_issue() -> str:
"""统计我在openEuler社区所负责的issue"""
try:
# 执行oegitext命令并解析结果
result = subprocess.check_output(['oegitext', 'show', 'issue', '-p'],
text=True,
stderr=subprocess.STDOUT)
return result
except subprocess.CalledProcessError as e:
return e
except Exception as e:
return e
if __name__ == "__main__":
# Initialize
mcp.run()3、openEuler MCP环境搭建
打开DevStation预安装的vscodium软件,在插件市场里安装Roo Code(后续也可以使用EulerCopilot实现)
在设置当中配置大模型,我们使用的是DeepSeeK V3的API:
API提供商:OpenAI Compatible
OpenAI基础URL:https://api.siliconflow.cn
密钥:对应的密钥
模型:Pro/deepseek-ai/DeepSeek-V3 #可以自己选择合适的模型在Roo Code插件上方的选项卡里选择MCP服务器
点击编辑全局MCP
{
"mcpServers": {
"oegitext_mcp": {
"command": "/usr/bin/uv",
"args": [
"--directory",
"/home/xxx/oegitext_mcp",
"run",
"--python",
"/usr/bin/python3",
"oegitext_mcp.py"
],
"disabled": false,
"autoApprove": [],
"alwaysAllow": []
},
}
}上面的路径修改成正确的实际路径,之后保存,点击完成
4、MCP Client调用效果

Frequently asked questions
What is mcp-servers?
mcp-servers is openEuler MCP Servers
How do I install mcp-servers?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-servers open source?
Yes — it is hosted on GitHub at https://github.com/openeuler-mirror/mcp-servers.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP