Cloudinary Structured Metadata MCP server

Cloudinary Structured Metadata MCP Server

Summary

Table of Contents

• Cloudinary Structured Metadata MCP Server
  • Installation
  • Configuration
  • Authentication
  • Available Tools
• Development
  • Building from Source
  • Contributions
  • Progressive Discovery

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:

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:

{
  "command": "npx",
  "args": [
    "@cloudinary/structured-metadata-mcp",
    "start",
    "--api-key",
    "",
    "--api-secret",
    "",
    "--cloud-name",
    ""
  ]
}

claude mcp add CloudinarySMD -- npx -y @cloudinary/structured-metadata-mcp start --api-key  --api-secret  --cloud-name 

gemini mcp add CloudinarySMD -- npx -y @cloudinary/structured-metadata-mcp start --api-key  --api-secret  --cloud-name 

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

{
  "command": "npx",
  "args": [
    "@cloudinary/structured-metadata-mcp",
    "start",
    "--api-key",
    "",
    "--api-secret",
    "",
    "--cloud-name",
    ""
  ]
}

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

{
  "command": "npx",
  "args": [
    "@cloudinary/structured-metadata-mcp",
    "start",
    "--api-key",
    "",
    "--api-secret",
    "",
    "--cloud-name",
    ""
  ]
}

npx @cloudinary/structured-metadata-mcp start --api-key  --api-secret  --cloud-name 

For a full list of server arguments, run:

npx @cloudinary/structured-metadata-mcp --help

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"
  }
}

Available Tools

The MCP server exposes Cloudinary's Structured Metadata API as tools. Use your AI application to discover and invoke the available tools for managing metadata fields and rules.

Usage Examples

Example 1: Manage Metadata Fields

1. List fields: "Show me all metadata fields in my account"
2. Create field: "Create a metadata field named 'category' of type 'enum' with values 'product,service,other'"
3. Get field: "Get details for the metadata field 'category'"
4. Update field: "Update the 'category' field to add a new value 'subscription'"
5. Delete field: "Delete the metadata field 'old_field'"

Example 2: Manage Field Datasources

1. Search datasource: "Search for values in the 'category' field datasource"
2. Update datasource: "Add a new value 'enterprise' to the 'category' field datasource"
3. Delete datasource entry: "Remove the value 'old_value' from the 'category' field"
4. Restore datasource: "Restore a deleted datasource entry for field 'category'"

Example 3: Manage Metadata Rules

1. List rules: "Show all metadata rules configured in my account"
2. Create rule: "Create a metadata rule to auto-tag assets in folder 'products' with category 'product'"
3. Update rule: "Update metadata rule [rule-id] to change the target folder"
4. Delete rule: "Delete metadata rule [rule-id]"

Example 4: Reorder Metadata Fields

1. Reorder single field: "Move the 'priority' metadata field to position 2"
2. Reorder multiple fields: "Reorder metadata fields: set 'category' to position 1, 'priority' to position 2"

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/structured-metadata-mcp.git
cd structured-metadata-mcp

# Install dependencies
npm install

# Build the project
npm run build

# Run locally
npm start

Project Structure

structured-metadata-mcp/
├── src/
│   ├── hooks/              # Custom authentication hooks
│   ├── mcp-server/         # MCP server implementation
│   │   ├── server.ts       # Main server (auto-generated)
│   │   └── tools/          # Generated tool wrappers
│   ├── funcs/              # API function implementations
│   └── models/             # Type definitions
├── .github/
│   └── workflows/          # CI/CD workflows
└── .speakeasy/             # Speakeasy configuration

Contributions

While we value contributions to this MCP Server, the code is generated programmatically. Any manual changes to generated files will be overwritten on the next generation.

What you can contribute:

• ✅ Custom hooks in src/hooks/
• ✅ Documentation improvements
• ✅ 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

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

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": {
    "CloudinarySMD": {
      "command": "npx",
      "args": ["@cloudinary/structured-metadata-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:

{
  "mcpServers": {
    "CloudinarySMD": {
      "command": "npx",
      "args": ["@cloudinary/structured-metadata-mcp", "start", "--mode", "dynamic", "--scope", "admin"],
      // ... other server arguments
    }
  }
}