How to Use the ImageKit (Media Optimization & DAM) MCP in Claude Code

Q: How does ImageKit (Media Optimization & DAM) handle custom fields in Claude Code?

The agent uses listcustomfields to display active metadata fields. It can also create new fields using createcustomschema from your terminal.

Drive your media optimization pipeline from the command line with Claude Code and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ImageKit (Media Optimization & DAM) MCP to Claude Code

Create your Vinkius account to connect ImageKit (Media Optimization & DAM) to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup ImageKit (Media Optimization & DAM) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless media audits via the CLI

The `list_media_files` tool retrieves your complete asset directory. Claude Code uses this MCP tool directly in your terminal session to pipe raw file lists into shell scripts. You can inspect individual files by running `get_file_details`. This returns CDN URLs, dimensions, and file types without requiring you to log into a browser dashboard.

Terminal-driven CDN cache invalidation

The `purge_cdn_cache` tool executes immediate cache clears across all edge servers from your terminal. Claude Code chains this tool inside your deployment workflows to force updates right after a build completes. It monitors the invalidation process using `get_purge_status`. You get instant terminal output showing whether the CDN has finished distributing your updated assets.

Automated MCP Server schemas and asset pruning

The `create_custom_schema` tool builds new metadata structures for your media files using JSON payloads. Claude Code sets up these schemas during database migrations or backend updates to keep your media tags synced. For storage maintenance, the agent uses `wipe_batch_assets` to drop old media assets. It can also target specific files with `wipe_media_asset` to automate your storage cleanup scripts.

Setup guide

Set up ImageKit (Media Optimization & DAM) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see imagekit-media-optimization-dam-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest ImageKit (Media Optimization & DAM) transactions." It will automatically discover and invoke the available ImageKit (Media Optimization & DAM) tools.

Terminal

claude mcp add --transport http imagekit-media-optimization-dam-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the ImageKit (Media Optimization & DAM) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "imagekit-media-optimization-dam-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ImageKit. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect ImageKit (Media Optimization & DAM) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about ImageKit (Media Optimization & DAM) MCP in Claude Code

You run a terminal query asking the agent to list your assets. It uses `list_media_files` to fetch the details and formats them directly in your CLI.

Yes. You can command the agent to purge a path. It executes `purge_cdn_cache` and outputs the invalidation ID directly to your terminal.

The agent uses `list_custom_fields` to display active metadata fields. It can also create new fields using `create_custom_schema` from your terminal.

You can ask the agent to delete specific assets. It will use `wipe_media_asset` for single files or `wipe_batch_assets` to purge multiple files in one command.

No. This MCP server runs locally in your terminal environment. It only transmits metadata queries and CDN purge requests directly to the official API endpoints using your local credentials.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript