How to Use the Canto MCP in AutoGen

Q: Is it possible for AutoGen agents to debate deleting a Canto asset?

Absolutely. A 'cleanup' agent can propose using wipemediaasset, but a 'security' agent can use getimagemetadata to check for retention tags and veto the action. The deletion only happens if they reach a consensus.

Q: How does the Canto MCP server connect to my AutoGen group chat?

You simply provide the server's URL to the mcpservertools function. This generates a list of Python functions you pass to your AssistantAgent. AutoGen's McpToolAdapter handles the rest automatically.

Let your AutoGen agents debate and agree on the best way to organize your Canto library. Collaboration, automated.

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 AutoGen

Create your Vinkius account to connect Canto 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 Canto with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborate on library organization

This isn't about one agent making a call. It's about a conversation. A 'Creative' agent can propose a new folder structure using `create_canto_folder`. A 'Librarian' agent can then challenge that plan, using `list_canto_folders` to point out an existing, similar structure. Through debate, they converge on the right plan. The final action is a result of consensus, not a single command. You're building a team that discusses the best way to manage your Canto assets.

Build a Canto review team with AutoGen agents

Metadata isn't always objective. Set up an 'SEO' agent to find an image with `global_asset_search` and propose new keywords. It suggests a `patch_image_metadata` call. A 'Brand' agent then reviews the proposal and can approve or reject it. This conversational workflow ensures changes are vetted. The agents debate the merits of different tags, and the final metadata is stronger because of it. The user can even step in as a proxy to settle disputes.

Get consensus before making destructive changes

Deleting assets is risky. With AutoGen, you can build a safety net. A 'Cleanup' agent can identify an old asset and propose using `wipe_media_asset` to delete it. But a 'Compliance' agent automatically intervenes, calling `get_image_metadata` to check for a 'legal hold' tag. If the tag exists, the 'Compliance' agent rejects the deletion. The `wipe_media_asset` tool is never called. This multi-agent review process prevents costly mistakes by forcing a discussion before any irreversible action is taken.

Setup guide

Set up Canto 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 Canto 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="Canto_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Canto 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="Canto_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Canto 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 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 AutoGen

It's a conversation. One agent proposes creating an album with `create_canto_album`. A second agent can then use `list_canto_albums` to check if a better option already exists, and they debate until they agree on a plan.

Yes, this is a core AutoGen pattern. One agent suggests a change by preparing a `patch_image_metadata` call. A UserProxy or another verification agent must then approve the call before it's actually executed by the MCP server.

Absolutely. A 'cleanup' agent can propose using `wipe_media_asset`, but a 'security' agent can use `get_image_metadata` to check for retention tags and veto the action. The deletion only happens if they reach a consensus.

You simply provide the server's URL to the `mcp_server_tools` function. This generates a list of Python functions you pass to your AssistantAgent. AutoGen's McpToolAdapter handles the rest automatically.

The asset metadata is passed as arguments within the agent conversation, intended for tool calls. The Vinkius server that executes these calls is completely stateless. It processes the request in a temporary, secure sandbox and keeps no record of your data.

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