by qiniu
Qiniu MCP Server is a Model Context Protocol (MCP) Server built on Qiniu Cloud products, enabling AI large model clients to access Qiniu Cloud Storage and intelligent multimedia services.
Qiniu MCP Server is a Model Context Protocol (MCP) Server that leverages Qiniu Cloud products to provide AI large model clients with access to Qiniu Cloud Storage and intelligent multimedia services. It acts as an intermediary, allowing AI models to interact with cloud resources within their context.
To use Qiniu MCP Server, you generally follow these steps:
For developers, you can clone the repository, set up a Python virtual environment, install dependencies using uv pip install -e .
, and configure environment variables in a .env
file with your Qiniu credentials and bucket information. You can then run the server in stdio or SSE mode.
Qiniu MCP Server offers the following capabilities:
Qiniu MCP Server is designed for scenarios where AI large models need to interact with cloud storage and multimedia services. Specific use cases include:
uv
package manager.uv
?
brew install uv
.curl -LsSf https://astral.sh/uv/install.sh | sh
and add the installation path to your PATH
environment variable.powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
.Error: spawn uvx ENOENT
when using Claude?
uvx
in the command parameter (e.g., /usr/local/bin/uvx
).uv --directory . run qiniu-mcp-server
or uv --directory . run qiniu-mcp-server --transport sse --port 8000
respectively.基于七牛云产品构建的 Model Context Protocol (MCP) Server,支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储、智能多媒体服务等。
关于访问七牛云存储详细情况请参考 基于 MCP 使用大模型访问七牛云存储。
能力集:
如果还没有安装 uv,可以使用以下命令安装:
# Mac,推荐使用 brew 安装
brew install uv
# Linux & Mac
# 1. 安装
curl -LsSf https://astral.sh/uv/install.sh | sh
# 2. 安装完成后,请确保将软件包安装路径(包含 uv 和 uvx 可执行文件的目录)添加到系统的 PATH 环境变量中。
# 假设安装包路径为 /Users/xxx/.local/bin(见安装执行输出)
### 临时生效(当前会话),在当前终端中执行以下命令:
export PATH="/Users/xxx/.local/bin:$PATH"
### 永久生效(推荐),在当前终端中执行以下命令:
echo 'export PATH="/Users/xxx/.local/bin:$PATH"' >> ~/.bash_profile
source ~/.bash_profile
# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
具体安装方式参考 uv 安装
步骤:
{
"mcpServers": {
"qiniu": {
"command": "uvx",
"args": [
"qiniu-mcp-server"
],
"env": {
"QINIU_ACCESS_KEY": "YOUR_ACCESS_KEY",
"QINIU_SECRET_KEY": "YOUR_SECRET_KEY",
"QINIU_REGION_NAME": "YOUR_REGION_NAME",
"QINIU_ENDPOINT_URL": "YOUR_ENDPOINT_URL",
"QINIU_BUCKETS": "YOUR_BUCKET_A,YOUR_BUCKET_B"
},
"disabled": false
}
}
}
注: cursor 中创建 MCP Server 可直接使用上述配置。 claude 中使用时可能会遇到:Error: spawn uvx ENOENT 错误,解决方案:command 中 参数填写 uvx 的绝对路径,eg: /usr/local/bin/uvx
# 克隆项目并进入目录
git clone git@github.com:qiniu/qiniu-mcp-server.git
cd qiniu-mcp-server
uv venv
source .venv/bin/activate # Linux/macOS
# 或
.venv\Scripts\activate # Windows
uv pip install -e .
复制环境变量模板:
cp .env.example .env
编辑 .env
文件,配置以下参数:
# S3/Kodo 认证信息
QINIU_ACCESS_KEY=your_access_key
QINIU_SECRET_KEY=your_secret_key
# 区域信息
QINIU_REGION_NAME=your_region
QINIU_ENDPOINT_URL=endpoint_url # eg:https://s3.your_region.qiniucs.com
# 配置 bucket,多个 bucket 使用逗号隔开,建议最多配置 20 个 bucket
QINIU_BUCKETS=bucket1,bucket2,bucket3
扩展功能,首先在 core 目录下新增一个业务包目录(eg: 存储 -> storage),在此业务包目录下完成功能拓展。
在业务包目录下的 __init__.py
文件中定义 load 函数用于注册业务工具或者资源,最后在 core
目录下的 __init__.py
中调用此 load 函数完成工具或资源的注册。
core
├── __init__.py # 各个业务工具或者资源加载
└── storage # 存储业务目录
├── __init__.py # 加载存储工具或者资源
├── resource.py # 存储资源扩展
├── storage.py # 存储工具类
└── tools.py # 存储工具扩展
强烈推荐使用 Model Control Protocol Inspector 进行测试。
# node 版本为:v22.4.0
npx @modelcontextprotocol/inspector uv --directory . run qiniu-mcp-server
uv --directory . run qiniu-mcp-server
uv --directory . run qiniu-mcp-server --transport sse --port 8000
Reviews feature coming soon
Stay tuned for community discussions and feedback