How to Use the Canto MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK pipeline search for specific assets in Canto?

Yes, your agent uses globalassetsearch to query files by their metadata properties. The OpenAI Agents SDK parses these search results and passes them to other specialized agents in your workflow.

Q: How do I handle destructive actions like deleting a Canto file with OpenAI Agents SDK?

You use the wipemediaasset tool inside your Python code. OpenAI Agents SDK lets you configure runtime guardrails to intercept this call and require manual approval before the asset is deleted.

Q: What is the setup process for this integration?

Run pip install openai-agents and initialize the MCP client with your Vinkius URL. Pass this instance to your agent constructor with tool caching enabled for optimal speed.

Control your Canto media library directly from your production Python pipelines using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Canto MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure Canto Asset Discovery and Retrieval

`global_asset_search` queries your media library to find specific images based on metadata constraints. Your OpenAI Agents SDK pipeline uses this tool to scan the Canto registry, locate files, and feed the results directly into downstream vision agents. Running this inside OpenAI's runtime means you track every asset query in your central dashboard. You get absolute visibility into how your agents navigate the media library using our MCP Server.

Structured Album Mutations with OpenAI Agents SDK

`create_canto_album` modifies your Web CRM boundaries by establishing new collections in your asset library. The OpenAI Agents SDK executes this tool to organize raw uploads, grouping them into structured folders based on runtime context. You define strict validation rules so your agents never create empty or mislabeled folders. This MCP Server handles the actual API handshake, ensuring your media structure matches your database state exactly.

Destructive Asset Wiping and Metadata Patches

`wipe_media_asset` deletes files from your media library and drops the corresponding database bytes immediately. Because this tool is destructive, your OpenAI Agents SDK system triggers pre-execution guardrails to verify the agent has permission before executing the delete. This MCP Server integration ensures safety. For safer updates, `patch_image_metadata` applies validation checks before rewriting metadata fields. You get clean, verified updates to your Canto assets without risking accidental data loss.

Setup guide

Set up Canto 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 Canto tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Canto 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="Canto Agent",
            instructions="You have access to Canto 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 Canto. 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 Canto 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 Canto MCP in OpenAI Agents SDK

It connects via a streamable HTTP server using the Vinkius endpoint. Your Python code registers the Canto MCP Server directly in the Agent constructor, letting your agents call media management tools instantly.

Yes, your agent uses `global_asset_search` to query files by their metadata properties. The OpenAI Agents SDK parses these search results and passes them to other specialized agents in your workflow.

You use the `wipe_media_asset` tool inside your Python code. OpenAI Agents SDK lets you configure runtime guardrails to intercept this call and require manual approval before the asset is deleted.

Run `pip install openai-agents` and initialize the MCP client with your Vinkius URL. Pass this instance to your agent constructor with tool caching enabled for optimal speed.

Your Canto asset data and metadata schemas remain sandboxed within V8 isolates on Vinkius. Every transaction is ephemeral, meaning no raw image files or structural metadata are stored on the host after the tool execution completes.

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