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

Q: How do AutoGen agents verify CDN purges with ImageKit (Media Optimization & DAM)?

An agent initiates the clear with purgecdncache, then passes the purge ID to a monitoring agent. That agent polls getpurgestatus until the edge confirms the cache is clean.

Q: Can agents modify custom metadata fields?

Absolutely. Your agents use listcustomfields to understand the schema, then apply updates using patchfiledetails based on their analysis of the media files.

Let AutoGen agents debate and coordinate ImageKit (Media Optimization & DAM) file purges and metadata updates.

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 AutoGen

Create your Vinkius account to connect ImageKit (Media Optimization & DAM) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage media workflows with AutoGen

`list_media_files` feeds asset lists to a storage agent that flags old files for deletion. A second security agent reviews the list before calling `wipe_batch_assets` on this MCP Server to clean up your storage. This multi-agent debate prevents accidental data loss in production. The agents negotiate based on usage patterns, ensuring only truly stale assets are removed.

Coordinate CDN invalidation using this MCP Server

`purge_cdn_cache` is triggered by a deployment agent when new media assets are published. A performance agent then uses `get_purge_status` to monitor the edge propagation until it completes. By separating execution and monitoring, your agents ensure cache updates don't impact site performance. They only signal success once the CDN edge is completely updated.

Validate custom schemas via agent consensus

`create_custom_schema` defines the metadata rules that your media assets must follow. A validation agent uses `get_exif_metadata` to check incoming files, while another agent uses `patch_file_details` to correct any errors. This collaborative loop ensures all assets match your corporate standards. The agents use `list_custom_fields` to verify compliance before files go live.

Setup guide

Set up ImageKit (Media Optimization & DAM) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes ImageKit (Media Optimization & DAM) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="ImageKit (Media Optimization & DAM)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ImageKit (Media Optimization & DAM) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="ImageKit (Media Optimization & DAM)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ImageKit (Media Optimization & DAM) data")
    print(result.messages[-1].content)

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 AutoGen

Use the MCP tool adapter with your Vinkius connection URL. Pass the generated tools list to your AssistantAgent constructor to give your agents access to the media API.

Yes. You can set up a multi-agent consensus loop where one agent proposes a deletion using `wipe_media_asset` and a supervisor agent must approve it before execution.

An agent initiates the clear with `purge_cdn_cache`, then passes the purge ID to a monitoring agent. That agent polls `get_purge_status` until the edge confirms the cache is clean.

Absolutely. Your agents use `list_custom_fields` to understand the schema, then apply updates using `patch_file_details` based on their analysis of the media files.

Vinkius manages the MCP Server in an isolated V8 sandbox with zero-trust architecture. It only processes the specific file paths, metadata payloads, and CDN logs required to execute the active tools, keeping your primary media storage secure.

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