How to Use the Brandfolder MCP in OpenAI Agents SDK

Q: How do I configure Brandfolder in my OpenAI Agents SDK project?

Instantiate the MCPServerStreamableHttp client with your Vinkius endpoint URL. Pass the server instance into your Agent constructor within the mcpservers list to register all ten asset tools.

Q: Can OpenAI Agents SDK handle asset deletion in Brandfolder safely?

Yes, the agent uses wipemediaasset to delete files. You can configure execution guardrails in the SDK to require human approval before the agent permanently deletes any asset.

Q: Does OpenAI Agents SDK support searching Brandfolder collections?

The agent uses the getcollectionassets tool to pull files from specific collections. It parses the collection ID and returns the asset metadata directly into the agent's context.

Q: How does the agent know which organization to access?

The server runs listplatformorganizations to identify accessible tenants. Your agent reads this list and selects the correct organization ID before querying assets.

Build production-grade agents with OpenAI Agents SDK that search, modify, and delete Brandfolder assets securely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Brandfolder MCP to OpenAI Agents SDK

Create your Vinkius account to connect Brandfolder to OpenAI Agents SDK 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 Brandfolder with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated asset ingestion with safety guardrails

The `create_cms_asset` tool inserts new files directly into your Brandfolder workspace from your agent. Your Python agent triggers this whenever a design asset is ready, bypassing manual uploads. OpenAI Agents SDK routes this action through validation chains before the upload hits production. This setup prevents your agent from pushing corrupted files or unauthorized file types into your asset library.

Metadata sync across production pipelines

The `patch_cms_asset` tool updates tags, descriptions, and custom fields on existing digital assets. It changes properties in place, ensuring your asset metadata matches your external database values. By declaring this tool in your agent configuration, you expose our MCP Server tools to specialized agents that handle metadata cleanup tasks. The SDK traces these updates on your OpenAI dashboard, so you always know which agent changed a file.

Fast CDN asset retrieval via MCP Server

The `list_asset_attachments` tool pulls the direct CDN delivery URLs and attachments associated with a specific asset. It bypasses the web UI to feed high-resolution assets directly into your production pipelines. We built this MCP Server to feed exact file locations to your OpenAI Agents SDK configuration. The framework caches these tool definitions, saving round-trips when your agent needs to fetch multiple URLs.

Setup guide

Set up Brandfolder MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Brandfolder tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Brandfolder tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Brandfolder tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Brandfolder Agent",
            instructions="You have access to Brandfolder tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Brandfolder. 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 Brandfolder 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 Brandfolder MCP in OpenAI Agents SDK

Instantiate the `MCPServerStreamableHttp` client with your Vinkius endpoint URL. Pass the server instance into your `Agent` constructor within the `mcp_servers` list to register all ten asset tools.

Yes, the agent uses `wipe_media_asset` to delete files. You can configure execution guardrails in the SDK to require human approval before the agent permanently deletes any asset.

The agent uses the `get_collection_assets` tool to pull files from specific collections. It parses the collection ID and returns the asset metadata directly into the agent's context.

The server runs `list_platform_organizations` to identify accessible tenants. Your agent reads this list and selects the correct organization ID before querying assets.

Vinkius runs this server inside an isolated V8 sandbox. Your API keys and asset metadata never touch persistent storage, and all communication uses TLS encryption.

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