Cloudinary Asset Management

io.github.cloudinary由 GitHub 帳號 cloudinary 發布v0.11.6更新於 Nov 19, 2026

Upload, generate, organize, search, and transform images, videos, and files with AI-powered tools.

發布方自己的服務:Cloudinary Analysis

已驗證Streamable HTTP可網頁執行檔案與儲存媒體與設計AI 與機器學習

概覽

AI 產生的概覽

Cloudinary 資產管理讓助手在 Cloudinary 帳戶中上傳、搜尋、整理、轉換與生成圖片、影片和檔案。

可以做什麼
  • 上傳、檢視、更新、重新命名與刪除圖片、影片及原始檔案
  • 為素材加上標籤,設定情境與結構化中繼資料,並建立素材之間的關聯
  • 依標籤、資料夾、格式、中繼資料、日期或視覺相似度搜尋;建立、移動與刪除資料夾
  • 透過縮放、裁切、格式轉換與特效建立或移除衍生版本
  • 依提示詞生成圖片、編輯既有圖片,並把圖片製作成短影片(測試版)
  • 將素材歸入可分享的合集,打包成 ZIP 或 TGZ 封存檔,並查看帳戶用量
適用情境
適合媒體素材存放在 Cloudinary,且希望助手在對話中直接尋找、清理、標記、轉換或生成素材的情況。也適用於需要批次上傳、資料夾整理、可分享合集或封存檔的行銷與商品目錄流程。
執行需求
可使用遠端端點,或透過 npm(需 Node.js 20.19.0 以上)或 Docker 在本機執行。需要 Cloudinary 雲端名稱以及 API key 與 API secret,可透過 CLOUDINARY_CLOUD_NAME、CLOUDINARY_API_KEY、CLOUDINARY_API_SECRET,或 cloudinary-* 標頭,或單一 CLOUDINARY_URL 提供。遠端端點宣告使用 OAuth。
安裝前請注意
API key 與 secret 可控制整個 Cloudinary 帳戶,請勿寫入共用設定或日誌。工具可刪除素材與資料夾、覆寫中繼資料、使 CDN 快取失效,並將合集發布到公開頁面,執行前應先確認。圖片與影片生成及轉換會消耗帳戶額度,且可能以長時間任務執行。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Cloudinary Asset Management,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/io.github.cloudinary%2Fasset-management-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-asset-management": {
      "type": "http",
      "url": "https://asset-management.mcp.cloudinary.com/mcp"
    }
  }
}

README

Cloudinary Asset Management MCP Server

Summary

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/asset-management-mcp",    "start",    "--api-key",    "",    "--api-secret",    "",    "--cloud-name",    ""  ]}
Claude Code CLI
bash
claude mcp add CloudinaryAssetMgmt -- npx -y @cloudinary/asset-management-mcp start --api-key  --api-secret  --cloud-name 
Gemini
bash
gemini mcp add CloudinaryAssetMgmt -- npx -y @cloudinary/asset-management-mcp start --api-key  --api-secret  --cloud-name 
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/asset-management-mcp",    "start",    "--api-key",    "",    "--api-secret",    "",    "--cloud-name",    ""  ]}
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/asset-management-mcp",    "start",    "--api-key",    "",    "--api-secret",    "",    "--cloud-name",    ""  ]}
Stdio installation via npm To start the MCP server, run:
bash
npx @cloudinary/asset-management-mcp start --api-key  --api-secret  --cloud-name 

For a full list of server arguments, run:

npx @cloudinary/asset-management-mcp --help

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_COLLECT_HEADERSCollect API response headers (see below)No
CLOUDINARY_MCP_APPSOverride MCP Apps default (see MCP Apps)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

Response Header Collection

You can configure the server to include Cloudinary API response headers (such as x-request-id and rate limit info) in tool output. This is useful for debugging and monitoring.

Set CLOUDINARY_COLLECT_HEADERS to control which headers are collected:

bash
# Collect all response headersCLOUDINARY_COLLECT_HEADERS=true
# Collect specific headers by exact name (comma-separated)CLOUDINARY_COLLECT_HEADERS=x-request-id,x-featureratelimit-limit,x-featureratelimit-remaining
# Mix exact names, prefix matching, and regex matchingCLOUDINARY_COLLECT_HEADERS=x-request-id,prefix:x-featureratelimit-
Header matching specs

Each entry in the comma-separated list is matched against response header names:

FormatExampleBehaviour
exact namex-request-idmatches only x-request-id
prefix:<value>prefix:x-featureratelimit-matches any header starting with x-featureratelimit-
regex:<pattern>regex:ratelimitmatches any header whose name contains ratelimit

You can also set this via the CLOUDINARY_URL query parameter:

bash
CLOUDINARY_URL=cloudinary://API_KEY:API_SECRET@CLOUD_NAME?collect_headers=true

When enabled, collected headers appear in an _headers field in the tool response. When not set, no headers are collected and responses are unchanged.

MCP Apps

The server can expose interactive MCP UI Apps (spec-aligned with io.modelcontextprotocol/ui) that hosts can render alongside tool results — for example, an asset gallery for list results, a single-asset detail view, and an upload UI.

Apps are enabled by default. Use the --mcp-apps flag (available on both start and serve) or the CLOUDINARY_MCP_APPS environment variable to override this behaviour:

ValueEffect
unsetDefault — all apps enabled
bare --mcp-apps (no value), all, or trueEnable every app (same as default)
none or falseDisable every app (kill-switch)
comma-separated subset, e.g. asset-gallery,asset-detailsEnable only the listed apps

Available app names: asset-gallery, asset-details, asset-upload.

bash
# Disable all appsnpx @cloudinary/asset-management-mcp serve --mcp-apps none
# Enable only the gallerynpx @cloudinary/asset-management-mcp start --mcp-apps asset-gallery
# Disable via env varCLOUDINARY_MCP_APPS=none npx @cloudinary/asset-management-mcp start

Precedence: CLI flag > environment variable > built-in default.

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"  }}

Available Tools

The MCP server exposes Cloudinary's Asset Management API as tools. Use your AI application to discover and invoke the available tools for uploading, managing, searching, transforming, and generating your media assets.

  • Assets: upload, inspect, update, rename, and delete images, videos, and raw files
  • Tags and metadata: tag assets, set contextual and structured metadata, and relate assets to each other
  • Search: find assets by tags, folder, format, metadata, and dates, or by visual similarity
  • Folders: create, move, and delete folders in the media library
  • Transformations: create and remove derived versions: resize, crop, change format, apply effects
  • Image generation: create an image from a text prompt, or edit and combine existing images with a prompt
  • Video generation (Beta): animate an image from your account into a short video with a prompt
  • Collections: group assets into collections without moving them, and share a collection on a public page
  • Archives and usage: package assets as ZIP or TGZ files, and check account usage

Usage Examples

Example 1: Upload and Transform an Image
yaml
1. Upload a local image: "Upload file:///Users/me/photo.jpg to Cloudinary as 'hero-image'"2. Transform it: "Transform asset 'hero-image' with transformations 'c_fill,w_800,h_600/e_sharpen'"3. Get details: "Show me details for asset with ID [asset-id]"
Example 2: Generate and Edit Images
yaml
1. Generate an image: "Generate a product shot of a white sneaker on a pastel background and save it to my 'campaigns' folder"2. Edit it: "Using [asset-id] as the reference, replace the background with a city street at night"3. Check a long-running job: "What's the status of generation task [task-id]?"
Example 3: Generate a Video from an Image
yaml
1. Pick the source image: "Find the image with public ID 'sneaker-hero'"2. Start the job: "Turn asset [asset-id] into an 8-second 16:9 video of the camera slowly orbiting the sneaker"3. Get the result: "Check video generation job [job-id] and give me the video URL when it's done"
Example 4: Search and Organize Assets
yaml
1. Search for images: "Find all images with tag 'product' uploaded in the last 7 days"2. Create folder: "Create a new folder called 'summer-2024-products'"3. List assets: "Show me all video assets in the 'marketing' folder"
Example 5: Build and Share a Collection
yaml
1. Create it: "Create a collection called 'Spring launch'"2. Add assets: "Add all images tagged 'spring-2026' to the 'Spring launch' collection"3. Share it: "Publish the 'Spring launch' collection and give me the public page link"
Example 6: Asset Management Workflow
yaml
1. Upload multiple files: "Upload all images from folder /assets/new-products/"2. Add tags: "Update asset [asset-id] and add tags 'featured,homepage'"3. Get usage stats: "Show my Cloudinary account usage statistics"
Example 7: Generate Archive
yaml
1. Get transformation docs: "Show me the Cloudinary transformation reference"2. Apply transformations: "Transform 'banner' asset with 'c_scale,w_1200/f_auto,q_auto'"3. Create archive: "Generate a ZIP archive of all images with tag 'export-ready'"

Custom Tools

This MCP server includes two powerful custom tools:

get-tx-reference

Retrieves the complete Cloudinary transformation reference documentation.

When to use:

  • Before creating or modifying transformations
  • When user asks about image/video effects, resizing, cropping, filters

Example:

sh
Use get-tx-reference to learn about available transformations

transform-asset

Applies transformations to existing assets using Cloudinary's explicit API.

Parameters:

  • publicId - The asset's public ID
  • transformations - Transformation string (e.g., c_fill,w_300,h_200)
  • resourceType - Type: image, video, or raw (default: image)
  • invalidate - Invalidate CDN cache (default: false)

Example:

sh
Transform asset "sample" with transformations "c_fill,w_500,h_500/e_sepia"

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": {    "CloudinaryAssetMgmt": {      "command": "npx",      "args": ["@cloudinary/asset-management-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.
  • list_scopes: Lists the scopes available on the server.

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.

You can combine dynamic mode with scope and tool filters:

jsonc
{  "mcpServers": {    "CloudinaryAssetMgmt": {      "command": "npx",      "args": ["@cloudinary/asset-management-mcp", "start", "--mode", "dynamic", "--scope", "admin"],      // ... other server arguments    }  }}

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/asset-management-mcp.gitcd asset-management-mcp
# Install dependenciesnpm install
# Build the projectnpm run build
# Run locallynpm start

Project Structure

ini
asset-management-mcp/├── src/│   ├── hooks/              # SDK hooks (manual)│   │   ├── cloudinaryAuthHook.ts   # Auth & file:// handling│   │   ├── customHeadersHook.ts    # Inject custom request headers│   │   ├── responseHeadersHook.ts  # Collect response headers│   │   ├── userAgentHook.ts        # Build User-Agent string│   │   └── registration.ts         # Hook registration│   ├── mcp-server/         # MCP server implementation│   │   ├── server.ts             # Main server (auto-generated)│   │   ├── server.extensions.ts  # Custom tools & app wiring (manual)│   │   ├── tools/                # Generated tool wrappers│   │   └── apps/                 # MCP UI Apps (manual)│   │       ├── config.ts             # App registry & --mcp-apps parsing│   │       ├── cli-flag.ts           # stricli flag definition│   │       ├── extensions.ts         # Resource-template registration│   │       ├── uri.ts                # App URI helpers / tool-name injection│   │       ├── tool-hooks.ts         # Per-tool app hooks│   │       ├── app-shared.ts         # Shared app utilities│   │       ├── asset-gallery-app.ts  # List results gallery UI│   │       ├── asset-details-app.ts  # Single-asset detail UI│   │       └── asset-upload-app.ts   # Upload UI│   ├── funcs/              # API function implementations│   └── models/             # Type definitions├── .github/│   └── workflows/          # CI/CD workflows└── .speakeasy/             # Speakeasy configuration

Contributions

While we value contributions to this MCP Server, most of the code is generated programmatically from the Cloudinary API spec. Any manual changes to generated files will be overwritten on the next generation — please direct your changes to the manual extension points below.

What you can contribute:

  • Custom tools and server wiring in src/mcp-server/server.extensions.ts
  • MCP UI Apps in src/mcp-server/apps/ (gallery, details, upload, and new apps)
  • SDK hooks in src/hooks/ (auth, custom headers, response headers, user agent)
  • Documentation improvements (this README, JSDoc on manual files)
  • Bug reports and feature requests

Generated files (do not edit):

  • src/mcp-server/server.ts
  • src/mcp-server/tools/*.ts
  • src/funcs/*.ts
  • src/models/*.ts

When touching generated files is unavoidable, prefer updating the upstream spec or Speakeasy configuration in .speakeasy/ so the change survives regeneration.

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 177d9ab

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

3
  1. v0.11.6最新Nov 5, 2026
  2. v0.11.5Oct 23, 2026
  3. v0.8.1Sep 16, 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