How to Use the iZooto MCP in AutoGen

Q: How do I register the iZooto MCP Server with AutoGen?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP URL. This automatically registers tools like sendpush with your AssistantAgent instances.

Q: How do AutoGen agents manage iZooto audience segments?

Your agents can call listsegments to view existing options. If they decide a new target is needed, they coordinate to call createsegment with specific behavioral rules.

Let AutoGen agents debate and optimize your web push campaigns using real-time iZooto performance data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect iZooto MCP to AutoGen

Create your Vinkius account to connect iZooto 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 iZooto with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent campaign review

The `get_stats` tool exposes campaign performance metrics to your agent group. In an AutoGen setup, a copywriter agent drafts a notification, while an analyst agent checks past performance to critique the copy before anything goes live. Once both agents reach a consensus on the copy, they hand the payload to a deployment agent. This agent checks API connectivity using `check_izooto_status` and schedules the push, ensuring no unapproved messages slip through.

Consensus-driven audience targeting

The `list_audiences` tool provides a high-level overview of your current subscriber base. Your targeting agent analyzes this data to propose a segment, while a budget agent verifies the subscriber count using `get_subscriber_count` to ensure you stay within plan limits. If the audience size is too large or too small, the agents debate alternative filters. They then call `create_segment` to build the finalized group and deploy the campaign using `send_segment_push`.

Coordinate AutoGen workflows with an MCP Server

The `list_notifications` tool allows your agents to review previously sent alerts to avoid spamming subscribers. This MCP server handles the underlying API communication, allowing your agents to focus on negotiating campaign timing and content. By exposing tools like `get_notification` to the conversation loop, agents can cross-reference active alerts. This collaborative filtering prevents overlapping campaigns from irritating your audience.

Setup guide

Set up iZooto 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 iZooto 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="iZooto_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent iZooto 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 iZooto. 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 iZooto 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 iZooto MCP in AutoGen

Install `autogen-ext[mcp]` and use mcp_server_tools with your Vinkius HTTP URL. This automatically registers tools like `send_push` with your AssistantAgent instances.

Yes, one agent can draft the message while another checks historical click rates using `get_stats` to suggest edits. They only call `send_push` once both agree the copy is optimized.

Your agents can call `list_segments` to view existing options. If they decide a new target is needed, they coordinate to call `create_segment` with specific behavioral rules.

The conversation continues until the defined consensus threshold is met. No tools like `send_segment_push` are executed until the supervising agent approves the final plan.

Your API credentials are encrypted and stored solely on Vinkius. The MCP server operates inside a secure V8 sandbox, ensuring your private segment definitions and campaign metrics are never exposed to external agents.

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