by qiniu
Provides MCP endpoints that enable AI models to list buckets, retrieve file lists, upload and download files, generate download links, perform image scaling and rounding, and refresh or prefetch CDN resources on Qiniu cloud.
Enables AI applications to interact with Qiniu cloud storage, intelligent media services, and CDN directly through MCP calls, eliminating the need for custom SDK code.
uv pip install -e .
)..env.example
to .env
and fill in the required Qiniu credentials and bucket list.uv --directory . run qiniu-mcp-server
uv --directory . run qiniu-mcp-server --transport sse --port 8000
core/
with a load
function for custom tools or resources.Q: Which Python version is required? A: Python 3.12 or newer.
Q: Do I need to install uv
manually?
A: Yes; install via Homebrew, the provided script, or PowerShell as shown in the README.
Q: How many buckets can I configure? A: Up to 20 buckets (comma‑separated) is recommended.
Q: I see spawn uvx ENOENT
on Windows.
A: Supply the absolute path to the uvx
executable in the command
field (e.g., C:\Users\User\.local\bin\uvx
).
Q: Can I run the server in a container?
A: Yes; use the standard uv
commands inside the container after copying the source and .env
file.
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
Please log in to share your review and rating for this MCP.
{ "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_BUCKETS>" } } } }
Explore related MCPs that share similar capabilities and solve comparable challenges
by awslabs
Provides specialized servers that expose AWS capabilities through the Model Context Protocol, enabling AI assistants to retrieve up-to-date documentation, execute API calls, and automate infrastructure workflows directly within development environments.
by cloudflare
Provides a collection of Model Context Protocol servers that enable MCP‑compatible clients to interact with Cloudflare services such as Workers, Observability, Radar, and more, allowing natural‑language driven management of configurations, data, and operations.
by Flux159
Connects to a Kubernetes cluster and offers a unified MCP interface for kubectl, Helm, port‑forwarding, diagnostics, and non‑destructive read‑only mode.
by TencentEdgeOne
Deploy HTML, folders, or zip archives to EdgeOne Pages and instantly obtain a public URL for fast edge delivery.
by rishikavikondala
Provides Model Context Protocol tools for performing AWS S3 and DynamoDB operations, with automatic logging and audit access via the `audit://aws-operations` endpoint.
by confluentinc
Enables AI assistants to manage Confluent Cloud resources such as Kafka topics, connectors, and Flink SQL statements through natural‑language interactions.
by aliyun
Enables AI assistants to operate Alibaba Cloud resources such as ECS, Cloud Monitor, OOS and other services through seamless integration with Alibaba Cloud APIs via the Model Context Protocol.
by aws-samples
Retrieve PDF documents and other S3 objects through Model Context Protocol resources, enabling LLMs to pull data directly from AWS S3 buckets.
by kocierik
Connects to HashiCorp Nomad and exposes Model Context Protocol endpoints for job, deployment, node, allocation, variable, volume, ACL, Sentinel, and cluster management via a Go‑based server.