How to Use the PushEngage MCP in AutoGen

Let your AutoGen agents debate and execute PushEngage campaigns, ensuring high-impact notifications for every site visitor.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PushEngage MCP to AutoGen

Create your Vinkius account to connect PushEngage to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PushEngage with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate campaign strategy with AutoGen

Configure one agent to call `list_pushengage_triggers` while another critiques the timing. They negotiate the best time to run `send_pushengage_broadcast` based on current site traffic. This debate process prevents impulsive messaging. Your agents reach a consensus before any notification is actually sent to your users.

Analyze segments through agent consensus

Use multiple agents to review `list_pushengage_segments`. One agent focuses on segment growth, while the other checks for audience relevance before finalizing a broadcast list. This ensures your notifications reach the right people. By having agents challenge each other, you minimize the risk of sending irrelevant content to your segments.

Automate status monitoring

Assign a dedicated agent to poll `check_pushengage_status` regularly. If the API shows issues, this agent alerts the rest of your team to pause active campaigns. This creates a self-healing system. Your agents stay informed on the health of your integration, preventing errors during critical broadcast windows.

Setup guide

Set up PushEngage 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 PushEngage 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="PushEngage_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

They use a conversation-based model to weigh the pros and cons of a broadcast. Once they agree on the parameters, one agent triggers the send tool.

Yes, agents can exchange the segment list retrieved by the tool. This allows them to collaborate on which specific group to target next.

It is fully compatible. You pass the server tools to your agents, and they handle the tool execution within their conversation loop.

They list all available triggers and debate which one fits the current user context best. This deliberation leads to more precise notification timing.

Your subscriber list is handled only by the agent tasked with the broadcast. The data remains scoped to your secure conversation session.

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