How to Use the Unbounce MCP in AutoGen

Q: Can AutoGen help me audit multiple Unbounce pages?

Yes. You can assign one agent to read all pages and another agent to challenge that list by comparing it against the available domains, achieving a consensus on coverage gaps.

Q: What kind of data does the Unbounce server provide for AutoGen?

The MCP Server provides four tools: domains, leads, pages, and subaccounts. These give your agents the full context needed to deliberate on marketing strategy.

Q: How does AutoGen connect with Unbounce for complex tasks?

AutoGen doesn't just call tools; it makes agents debate about which tool to call, and in what order. This simulates human deliberation over a technical process.

Q: Which data type does the Unbounce server touch for privacy concerns?

The leads tool captures personal contact information (PCI) and submission metadata. Any agent consensus built around this data must prioritize security and compliance.

Have AI agents argue through Unbounce marketing data using AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unbounce MCP to AutoGen

Create your Vinkius account to connect Unbounce 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 Unbounce with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate which landing pages need immediate updates.

You set up a debate between agents. One agent might analyze all existing `pages` to find outdated structures. A second agent might use `leads` data to argue that the current conversion rate is too low for those pages, forcing a consensus on necessary changes before any deployment occurs.

Validate account structure and domain dependencies.

Agents can argue over permissions. A 'Security Agent' checks the scope by listing `sub_accounts`. Another agent might verify if a specific page requires a custom setup by checking both `pages` and available `domains`, forcing a decision on which environment is valid for deployment.

Ensure all required leads are captured and accounted for.

The system can simulate an audit. An agent pulls the list of potential lead sources using `pages`. Another challenges that list by cross-referencing it with the available custom domains (`domains`) to ensure every page has a valid target, achieving consensus on data gaps.

Setup guide

Set up Unbounce 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 Unbounce 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="Unbounce_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You give multiple agents competing goals. The agents then debate the best action sequence—for example, arguing whether to update a page or fix its associated domain first.

Yes. You can assign one agent to read all `pages` and another agent to challenge that list by comparing it against the available `domains`, achieving a consensus on coverage gaps.

The MCP Server provides four tools: `domains`, `leads`, `pages`, and `sub_accounts`. These give your agents the full context needed to deliberate on marketing strategy.

AutoGen doesn't just call tools; it makes agents *debate* about which tool to call, and in what order. This simulates human deliberation over a technical process.

The `leads` tool captures personal contact information (PCI) and submission metadata. Any agent consensus built around this data must prioritize security and compliance.

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