Cloudinary MCP Server
Cloudinary MCP 服务器
该 MCP 服务器提供通过 Claude Desktop 和兼容的 MCP 客户端将图像和视频上传到 Cloudinary 的工具。
安装
要求:Node.js
从nodejs.org安装 Node.js(版本 18 或更高版本)和 npm
验证安装:
node --version npm --version
使用 npx 安装(推荐)
导航到 Claude 配置目录:
Windows:
C:\Users\NAME\AppData\Roaming\ClaudemacOS:
~/Library/Application Support/Claude/
您还可以在 Claude Desktop 应用程序中找到这些目录:Claude Desktop > 设置 > 开发人员 > 编辑配置
将以下配置添加到您的 MCP 设置文件:
{
"mcpServers": {
"cloudinary": {
"command": "npx",
"args": ["@felores/cloudinary-mcp-server@latest"],
"env": {
"CLOUDINARY_CLOUD_NAME": "your_cloud_name",
"CLOUDINARY_API_KEY": "your_api_key",
"CLOUDINARY_API_SECRET": "your_api_secret"
}
}
}
}确保使用Cloudinary 控制台中的 Cloudinary 凭据替换环境变量。
开发人员安装
如果您想修改服务器或参与开发:
克隆存储库:
git clone https://github.com/felores/cloudinary-mcp-server.git
cd cloudinary-mcp-server安装依赖项并构建:
npm install
npm run buildRelated MCP server: Image Analysis MCP Server
设置说明
首先,确保您拥有 Cloudinary 帐户并从Cloudinary 控制台获取您的凭据:
云名称
API 密钥
API 秘密
将服务器配置添加到您的 Claude/Cline MCP 设置文件中:
{
"mcpServers": {
"cloudinary": {
"command": "node",
"args": ["c:/path/to/cloudinary-mcp-server/dist/index.js"],
"env": {
"CLOUDINARY_CLOUD_NAME": "your_cloud_name",
"CLOUDINARY_API_KEY": "your_api_key",
"CLOUDINARY_API_SECRET": "your_api_secret"
}
}
}
}对于 Claude 桌面应用程序,请在适合您的操作系统的位置编辑配置文件。
安装依赖项并构建服务器:
npm install
npm run build可用工具
上传
将图像和视频上传到 Cloudinary。
参数:
file(必需):要上传的文件路径、URL 或 base64 数据 URIresource_type(可选):资源类型(“图像”、“视频”或“原始”)public_id(可选):已上传资产的自定义公共 IDoverwrite(可选):是否覆盖具有相同公共 ID 的现有资产tags(可选):分配给已上传资产的标签数组
Claude/Cline 中的示例用法:
use_mcp_tool({
server_name: "cloudinary",
tool_name: "upload",
arguments: {
file: "path/to/image.jpg",
resource_type: "image",
public_id: "my-custom-id"
}
});Available Tools
1 tooluploadB
Upload media (images/videos) to Cloudinary. For large files, the upload is processed in chunks and returns a streaming response. The uploaded asset will be available at:
HTTP: http://res.cloudinary.com/{cloud_name}/{resource_type}/upload/v1/{public_id}.{format}
HTTPS: https://res.cloudinary.com/{cloud_name}/{resource_type}/upload/v1/{public_id}.{format} where {cloud_name} is your Cloudinary cloud name, resource_type is 'image' or 'video', and format is determined by the file extension.
Inputs: file (required), resource_type, public_id, overwrite, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility for ambiguity or overlap between tools. The 'upload' tool has a clear, singular purpose of uploading media to Cloudinary, making it impossible for an agent to misselect among multiple options.
Since there is only one tool named 'upload', it inherently follows a consistent naming pattern. There are no other tools to compare against, so no inconsistencies can arise in verb style, case conventions, or other naming aspects.
A single tool is too few for a Cloudinary server, which typically handles a wide range of media operations like upload, delete, transform, list, and fetch. This minimal set severely limits functionality and will likely cause agent failures due to missing essential operations for the domain.
The tool set is severely incomplete for a Cloudinary media management server. It only provides upload functionality, with glaring gaps such as no delete, update, list, search, or transformation tools. This makes it impossible for agents to perform basic CRUD or lifecycle operations in the domain.
Maintenance
Related MCP Connectors
Upload, generate, organize, search, and transform images, videos, and files with AI-powered tools.
Upload, generate, organize, search, and transform images, videos, and files with AI-powered tools.
MCP server exposing the YourImageShare upload API (upload/list/delete) as tools for AI agents.
Manage Cloudinary upload presets, named transformations, mappings, triggers, and streaming profiles.
Related MCP Servers
- AlicenseAqualityDmaintenanceThis server generates placeholder image URLs from various providers, supporting input validation and integration with desktop applications like Claude and Cursor.112MIT
- AlicenseCqualityDmaintenanceA server that accepts image URLs and analyzes their content using GPT-4-turbo, enabling Claude AI assistants to understand and describe images through natural language.28MIT
- AlicenseNot gradedqualityDmaintenanceA lightweight MCP server for image processing and cloud uploads that automates resizing, converting, optimizing, and uploading images to services like AWS S3, Cloudflare R2, and Google Cloud Storage.25 npm18MIT
- AlicenseAqualityDmaintenanceMCP server for uploading images to ImgBB from Claude-compatible clients.3MIT