Cloudinary Analysis

com.cloudinary由 cloudinary.com 發布官方發布者v0.5.3更新於 Nov 13, 2026

Run AI-powered analysis on images including moderation, captioning, tagging, and more.

已驗證Streamable HTTP可網頁執行媒體與設計AI 與機器學習

概覽

AI 產生的概覽

Cloudinary Analysis MCP 伺服器讓助理對圖片執行 AI 分析,包括內容審核、產生說明、標記、畫質與浮水印偵測。

可以做什麼
  • 對圖片執行 AI 視覺分析,包括標記、內容審核與一般描述
  • 為素材產生說明文字與文字類分析
  • 套用時尚、商品、文字、人體結構、Google 標記、浮水印偵測等專用分類器
  • 透過 Cloudinary Analyze API 分析外部素材,並依請求的分析類型回傳結果
  • 可選用動態模式,只暴露 list_tools、describe_tool_input、execute_tool 等中繼工具以節省上下文
適用情境
當你希望助理檢查 Cloudinary 帳戶中的圖片素材或外部連結,並回傳結構化標籤、說明、審核標記或畫質訊號,而不必自行撰寫 API 呼叫時適用。
執行需求
可使用遠端端點,或透過 npm 套件 @cloudinary/analysis-mcp(需 Node.js 20.19.0 以上)或 Docker 映像在本機執行。需要 Cloudinary 雲端名稱、API key 與 API secret,可透過 CLOUDINARY_CLOUD_NAME、CLOUDINARY_API_KEY、CLOUDINARY_API_SECRET 環境變數,cloudinary-cloud-name、cloudinary-api-key、cloudinary-api-secret 標頭,或單一 CLOUDINARY_URL 提供;亦宣告支援 OAuth。部分分析選項需訂閱對應的附加元件。
安裝前請注意
需要提供 Cloudinary API secret(CLOUDINARY_API_SECRET 或 cloudinary-api-secret 標頭),該金鑰可存取帳戶,請勿寫入共用設定或日誌。Analyze API 處於公開測試階段,部分分析選項需付費附加元件訂閱。提交的圖片素材與連結會傳送至 Cloudinary 處理。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Cloudinary Analysis,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.cloudinary%2Fanalysis-mcp/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "cloudinary-analysis": {
      "type": "http",
      "url": "https://analysis.mcp.cloudinary.com/mcp"
    }
  }
}

README

Cloudinary 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:

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.

Claude Desktop

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.

Cursor

[Install MCP Server]

Or manually:

  1. Open Cursor Settings
  2. Select Tools and Integrations
  3. Select New MCP Server
  4. If the configuration file is empty paste the following JSON into the MCP Server Configuration:
json
{  "command": "npx",  "args": [    "@cloudinary/analysis-mcp",    "start",    "--cloud-name",    "CLOUD_NAME",    "--api-key",    "",    "--api-secret",    "",    "--o-auth2",    ""  ]}
Claude Code CLI
bash
claude mcp add CloudinaryAnalysis -- npx -y @cloudinary/analysis-mcp start --cloud-name CLOUD_NAME --api-key  --api-secret  --o-auth2 
Gemini
bash
gemini mcp add CloudinaryAnalysis -- npx -y @cloudinary/analysis-mcp start --cloud-name CLOUD_NAME --api-key  --api-secret  --o-auth2 
Windsurf

Refer to Official Windsurf documentation for latest information

  1. Open Windsurf Settings
  2. Select Cascade on left side menu
  3. Click on Manage MCPs. (To Manage MCPs you should be signed in with a Windsurf Account)
  4. Click on View raw config to open up the mcp configuration file.
  5. If the configuration file is empty paste the full json
bash
{  "command": "npx",  "args": [    "@cloudinary/analysis-mcp",    "start",    "--cloud-name",    "CLOUD_NAME",    "--api-key",    "",    "--api-secret",    "",    "--o-auth2",    ""  ]}
VS Code

[Install in VS Code]

Or manually:

Refer to Official VS Code documentation for latest information

  1. Open Command Palette
  2. Search and open MCP: Open User Configuration. This should open mcp.json file
  3. If the configuration file is empty paste the full json
bash
{  "command": "npx",  "args": [    "@cloudinary/analysis-mcp",    "start",    "--cloud-name",    "CLOUD_NAME",    "--api-key",    "",    "--api-secret",    "",    "--o-auth2",    ""  ]}
Stdio installation via npm To start the MCP server, run:
bash
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:

jsonc
{  "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:

VariableDescriptionRequired
CLOUDINARY_CLOUD_NAMEYour Cloudinary cloud nameYes
CLOUDINARY_API_KEYYour Cloudinary API keyYes
CLOUDINARY_API_SECRETYour Cloudinary API secretYes
CLOUDINARY_URLComplete Cloudinary URL (alternative to individual vars)No

CLOUDINARY_URL Format

You can use a single CLOUDINARY_URL instead of individual variables:

bash
CLOUDINARY_URL=cloudinary://API_KEY:API_SECRET@CLOUD_NAME

Authentication

The MCP server uses your Cloudinary API key and secret for authentication:

json
{  "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

bash
# Clone the repositorygit clone https://github.com/cloudinary/analysis-mcp.gitcd analysis-mcp
# Install dependenciesnpm install
# Build the projectnpm run build
# Run locallynpm 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

來源:README.md,提交 4146c31

工具

0
該伺服器需要登入,因此 SourceWeft 無法在沒有帳號的情況下讀取其工具,也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v0.5.3最新Nov 13, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Cloudinary 整合