MCP server Cloudinary Analysis
Commit 12 de nov. de 2026Realize análises de imagem com IA, incluindo moderação, tagging, legendagem e avaliação de qualidade usando a Cloudinary Analyze API.
Também conhecido como cloudinary/analysis-mcp, analysis-mcp, @cloudinary/analysis-mcp
- Stars
- 0
- Ferramentas
- —
- Downloads, 30 dias
- 317
- Versão mais recente
- 0.5.3
- Último commit
- 12 de nov. de 2026
- Licença
- MIT
O que é o MCP Cloudinary Analysis?
Realize análises de imagem com IA, incluindo moderação, tagging, legendagem e avaliação de qualidade usando a Cloudinary Analyze API.
Resumo gerado a partir do README do projeto
Sobre o MCP server de Cloudinary Analysis
Analisar ativos externos em busca de detalhes visuais é o que os desenvolvedores fazem com o Cloudinary Analysis MCP server. Esta ferramenta conecta clientes de IA à Cloudinary Analyze API para realizar diversos tipos de inspeções automatizadas em imagens. Ela suporta uma ampla gama de funções especializadas, incluindo AI vision tagging, moderação, legendagem e detecção de anatomia humana. Também oferece recursos para verificar a qualidade da imagem, detectar marcas d'água e utilizar modelos específicos como Cld Fashion ou Shop Classifier.
Para usar este servidor, você deve fornecer um Cloudinary cloud name e se autenticar via Basic Authentication com uma API Key e API Secret ou via OAuth2. O servidor pode ser integrado em ambientes como Claude Desktop, Cursor, VS Code e Windsurf. Ele foi projetado para funcionar com Node.js 20.19.0 ou posterior. Como a Analyze API está em beta público, os usuários devem ter uma assinatura ativa dos add-ons relevantes da Cloudinary para acessar opções de análise específicas.
O que você pode fazer com ele
- 1Moderação de conteúdo automatizadaVerifique imagens em busca de conteúdo inadequado usando as ferramentas de moderação integradas.
- 2Gerar legendas descritivas para imagensCrie descrições de texto para imagens para melhorar a acessibilidade ou a busca.
- 3Avaliar a qualidade de ativos visuaisAvalie se as imagens enviadas atendem a padrões de qualidade específicos.
- 4Identificar itens de moda e varejoUse modelos especializados para classificar roupas ou conteúdos relacionados a compras.
Escrito a partir do README do projeto. Cada caso de uso é verificado com uma citação dele.
Como instalar o MCP Cloudinary Analysis
Formatos verificados em 10 nov 2026Adicionar ao CursorAdicionar ao GooseInstalar o MCP Cloudinary Analysis no Claude Code
$ claude mcp add --env 'CLOUDINARY_API_SECRET=<YOUR_CLOUDINARY_API_SECRET>' --env 'CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY>' --env 'CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME>' analysis-mcp -- npx -y @cloudinary/analysis-mcpInstalar o MCP Cloudinary Analysis no Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"analysis-mcp": {
"command": "npx",
"args": [
"-y",
"@cloudinary/analysis-mcp"
],
"env": {
"CLOUDINARY_API_SECRET": "<YOUR_CLOUDINARY_API_SECRET>",
"CLOUDINARY_API_KEY": "<CLOUDINARY_API_KEY>",
"CLOUDINARY_CLOUD_NAME": "<CLOUDINARY_CLOUD_NAME>"
}
}
}
}Instalar o MCP Cloudinary Analysis no VS Code
.vscode/mcp.json
{
"servers": {
"analysis-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cloudinary/analysis-mcp"
],
"env": {
"CLOUDINARY_API_SECRET": "<YOUR_CLOUDINARY_API_SECRET>",
"CLOUDINARY_API_KEY": "<CLOUDINARY_API_KEY>",
"CLOUDINARY_CLOUD_NAME": "<CLOUDINARY_CLOUD_NAME>"
}
}
}
}Instalar o MCP Cloudinary Analysis no VS Code CLI
$ code --add-mcp '{"name":"analysis-mcp","type":"stdio","command":"npx","args":["-y","@cloudinary/analysis-mcp"],"env":{"CLOUDINARY_API_SECRET":"<YOUR_CLOUDINARY_API_SECRET>","CLOUDINARY_API_KEY":"<CLOUDINARY_API_KEY>","CLOUDINARY_CLOUD_NAME":"<CLOUDINARY_CLOUD_NAME>"}}'Instalar o MCP Cloudinary Analysis no Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"analysis-mcp": {
"command": "npx",
"args": [
"-y",
"@cloudinary/analysis-mcp"
],
"env": {
"CLOUDINARY_API_SECRET": "<YOUR_CLOUDINARY_API_SECRET>",
"CLOUDINARY_API_KEY": "<CLOUDINARY_API_KEY>",
"CLOUDINARY_CLOUD_NAME": "<CLOUDINARY_CLOUD_NAME>"
}
}
}
}Instalar o MCP Cloudinary Analysis no Codex
$ codex mcp add analysis-mcp --env 'CLOUDINARY_API_SECRET=<YOUR_CLOUDINARY_API_SECRET>' --env 'CLOUDINARY_API_SECRET=<YOUR_CLOUDINARY_API_SECRET>' --env 'CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY>' --env 'CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY>' --env 'CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME>' --env 'CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME>' -- npx -y @cloudinary/analysis-mcpInstalar o MCP Cloudinary Analysis no Codex config.toml
~/.codex/config.toml
[mcp_servers.analysis-mcp] command = "npx" args = ["-y", "@cloudinary/analysis-mcp"] [mcp_servers.analysis-mcp.env] CLOUDINARY_API_SECRET = "<YOUR_CLOUDINARY_API_SECRET>" CLOUDINARY_API_KEY = "<CLOUDINARY_API_KEY>" CLOUDINARY_CLOUD_NAME = "<CLOUDINARY_CLOUD_NAME>"
Instalar o MCP Cloudinary Analysis no Gemini CLI
$ gemini mcp add -s user -e 'CLOUDINARY_API_SECRET=<YOUR_CLOUDINARY_API_SECRET>' -e 'CLOUDINARY_API_SECRET=<YOUR_CLOUDINARY_API_SECRET>' -e 'CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY>' -e 'CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY>' -e 'CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME>' -e 'CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME>' analysis-mcp npx -- -y @cloudinary/analysis-mcpInstalar o MCP Cloudinary Analysis no Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"analysis-mcp": {
"command": "npx",
"args": [
"-y",
"@cloudinary/analysis-mcp"
],
"env": {
"CLOUDINARY_API_SECRET": "<YOUR_CLOUDINARY_API_SECRET>",
"CLOUDINARY_API_KEY": "<CLOUDINARY_API_KEY>",
"CLOUDINARY_CLOUD_NAME": "<CLOUDINARY_CLOUD_NAME>"
}
}
}
}Configuração
CLOUDINARY_API_SECRETObrigatórioSecretoYour Cloudinary API secret. Found in Dashboard > Settings > Access Keys.
CLOUDINARY_API_SECRETObrigatórioSecretoYour Cloudinary API secret. Found in Dashboard > Settings > Access Keys.
CLOUDINARY_API_KEYObrigatórioYour Cloudinary API key. Found in Dashboard > Settings > Access Keys.
CLOUDINARY_API_KEYObrigatórioYour Cloudinary API key. Found in Dashboard > Settings > Access Keys.
CLOUDINARY_CLOUD_NAMEObrigatórioYour Cloudinary cloud name. Find it in your Cloudinary Dashboard.
CLOUDINARY_CLOUD_NAMEObrigatórioYour Cloudinary cloud name. Find it in your Cloudinary Dashboard.
CLOUDINARY_URL
| Nome | Descrição | Tipo |
|---|---|---|
| CLOUDINARY_API_SECRET | Your Cloudinary API secret. Found in Dashboard > Settings > Access Keys. | ObrigatórioSecreto |
| CLOUDINARY_API_SECRET | Your Cloudinary API secret. Found in Dashboard > Settings > Access Keys. | ObrigatórioSecreto |
| CLOUDINARY_API_KEY | Your Cloudinary API key. Found in Dashboard > Settings > Access Keys. | Obrigatório |
| CLOUDINARY_API_KEY | Your Cloudinary API key. Found in Dashboard > Settings > Access Keys. | Obrigatório |
| CLOUDINARY_CLOUD_NAME | Your Cloudinary cloud name. Find it in your Cloudinary Dashboard. | Obrigatório |
| CLOUDINARY_CLOUD_NAME | Your Cloudinary cloud name. Find it in your Cloudinary Dashboard. | Obrigatório |
| CLOUDINARY_URL | — |
Verificações automatizadas
Executado em 13 de nov. de 2026Relatório completo →Ainda não verificado. Um servidor precisa de uma pontuação de 80, nenhum problema grave e dados suficientes para verificarmos. Como as verificações funcionam · O que corrigir para ganhar mais pontos
- Repositório de origem vinculado e acessívelPassou
- Licença de código aberto (OSI)Passou
- Commit ou release no último anoPassou
- Nome do pacote não é próximo a um pacote popular@cloudinary/analysis-mcp looks like @amplitude/mcp-analyticsProblema encontrado
- O endpoint remoto usa HTTPSPassou
- Ferramentas destrutivas estão rotuladasNão verificado
- Sem instruções ocultas para o modeloPassou
- Nenhum aviso crítico no pacote ou em suas dependênciasPassou
README
Ver no GitHubCloudinary Analysis MCP Server
Summary
Analyze API (Beta): Use the Analyze API to analyze any external asset and return details based on the type of analysis requested.
Currently supports the following analysis options:
- AI Vision - Tagging
- AI Vision - Moderation
- AI Vision - General
- Captioning
- Cld Fashion
- Cld Text
- Coco
- Google Tagging
- Human Anatomy
- Image Quality Analysis
- Lvis
- Shop Classifier
- Unidet
- Watermark Detection
Notes:
- The Analyze API is currently in development and is available as a Public Beta, which means we value your feedback, so please feel free to share any thoughts with us.
- The analysis options require an active subscription to the relevant add-on. Learn more about registering for add-ons.
The API supports both Basic Authentication using your Cloudinary API Key and API Secret (which can be found on the Dashboard page of your Cloudinary Console) or OAuth2 (Contact support for more information regarding OAuth).
Table of Contents
Installation
The MCP server requires Node.js 20.19.0 or later.
Install the MCP server as a Desktop Extension using the pre-built mcp-server.mcpb file:
Simply drag and drop the mcp-server.mcpb file onto Claude Desktop to install the extension.
The MCP bundle package includes the MCP server and all necessary configuration. Once installed, the server will be available without additional setup.
[!NOTE] MCP bundles provide a streamlined way to package and distribute MCP servers. Learn more about Desktop Extensions.
Or manually:
- Open Cursor Settings
- Select Tools and Integrations
- Select New MCP Server
- If the configuration file is empty paste the following JSON into the MCP Server Configuration:
{
"command": "npx",
"args": [
"@cloudinary/analysis-mcp",
"start",
"--cloud-name",
"CLOUD_NAME",
"--api-key",
"",
"--api-secret",
"",
"--o-auth2",
""
]
}
claude mcp add CloudinaryAnalysis -- npx -y @cloudinary/analysis-mcp start --cloud-name CLOUD_NAME --api-key --api-secret --o-auth2
gemini mcp add CloudinaryAnalysis -- npx -y @cloudinary/analysis-mcp start --cloud-name CLOUD_NAME --api-key --api-secret --o-auth2
Refer to Official Windsurf documentation for latest information
- Open Windsurf Settings
- Select Cascade on left side menu
- Click on
Manage MCPs. (To Manage MCPs you should be signed in with a Windsurf Account) - Click on
View raw configto open up the mcp configuration file. - If the configuration file is empty paste the full json
{
"command": "npx",
"args": [
"@cloudinary/analysis-mcp",
"start",
"--cloud-name",
"CLOUD_NAME",
"--api-key",
"",
"--api-secret",
"",
"--o-auth2",
""
]
}
Or manually:
Refer to Official VS Code documentation for latest information
- Open Command Palette
- Search and open
MCP: Open User Configuration. This should open mcp.json file - If the configuration file is empty paste the full json
{
"command": "npx",
"args": [
"@cloudinary/analysis-mcp",
"start",
"--cloud-name",
"CLOUD_NAME",
"--api-key",
"",
"--api-secret",
"",
"--o-auth2",
""
]
}
npx @cloudinary/analysis-mcp start --cloud-name CLOUD_NAME --api-key --api-secret --o-auth2
For a full list of server arguments, run:
npx @cloudinary/analysis-mcp --help
Progressive Discovery
MCP servers with many tools can bloat LLM context windows, leading to increased token usage and tool confusion. Dynamic mode solves this by exposing only a small set of meta-tools that let agents progressively discover and invoke tools on demand.
To enable dynamic mode, pass the --mode dynamic flag when starting your server:
{
"mcpServers": {
"CloudinaryAnalysis": {
"command": "npx",
"args": ["@cloudinary/analysis-mcp", "start", "--mode", "dynamic"],
// ... other server arguments
}
}
}
In dynamic mode, the server registers only the following meta-tools instead of every individual tool:
list_tools: Lists all available tools with their names and descriptions.describe_tool_input: Returns the input schema for one or more tools by name.execute_tool: Executes a tool by name with its arguments.
This approach significantly reduces the number of tokens sent to the LLM on each request, which is especially useful for servers with a large number of tools.
Configuration
Environment Variables
The MCP server supports the following environment variables:
| Variable | Description | Required |
|---|---|---|
CLOUDINARY_CLOUD_NAME |
Your Cloudinary cloud name | Yes |
CLOUDINARY_API_KEY |
Your Cloudinary API key | Yes |
CLOUDINARY_API_SECRET |
Your Cloudinary API secret | Yes |
CLOUDINARY_URL |
Complete Cloudinary URL (alternative to individual vars) | No |
CLOUDINARY_URL Format
You can use a single CLOUDINARY_URL instead of individual variables:
CLOUDINARY_URL=cloudinary://API_KEY:API_SECRET@CLOUD_NAME
Authentication
The MCP server uses your Cloudinary API key and secret for authentication:
{
"env": {
"CLOUDINARY_CLOUD_NAME": "demo",
"CLOUDINARY_API_KEY": "123456789012345",
"CLOUDINARY_API_SECRET": "abcdefghijklmnopqrstuvwxyz12"
}
}
Development
Building from Source
Prerequisites
- Node.js v20 or higher
- npm, pnpm, bun, or yarn
Build Steps
# Clone the repository
git clone https://github.com/cloudinary/analysis-mcp.git
cd analysis-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Run locally
npm start
Contributions
While we value contributions to this MCP Server, the code is generated programmatically from the Cloudinary API spec. Any manual changes to generated files will be overwritten on the next generation.
We look forward to hearing your feedback. Feel free to open a PR or issue with a proof of concept and we'll do our best to include it in a future release.
MCP Server Created by Speakeasy
Perguntas sobre o MCP Cloudinary Analysis
Como adiciono o MCP Cloudinary Analysis ao Claude Code?
Execute claude mcp add --env 'CLOUDINARY_API_SECRET=<YOUR_CLOUDINARY_API_SECRET>' --env 'CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY>' --env 'CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME>' analysis-mcp -- npx -y @cloudinary/analysis-mcp no seu terminal. Adicione --scope user para torná-lo disponível em todos os projetos.
Como adiciono o MCP Cloudinary Analysis ao Cursor?
Abra ~/.cursor/mcp.json e adicione o servidor em mcpServers, usando a configuração do Cursor mostrada na seção de instalação acima.
Preciso de uma assinatura para usar essas ferramentas de análise?
Sim, as opções de análise específicas exigem uma assinatura ativa do add-on relevante da Cloudinary.
Como posso me autenticar no Cloudinary Analysis MCP server?
O servidor suporta Basic Authentication usando sua Cloudinary API Key e API Secret, ou OAuth2.
Quais são os requisitos de sistema para instalação?
O MCP server requer a versão 20.19.0 ou posterior do Node.js.