How to Use the FunnelCockpit MCP in AutoGen

Q: How do AutoGen agents decide which FunnelCockpit tool to use?

They talk it out. One agent might suggest using createcontact, but another might argue they need to getcontact first to avoid duplicates. The final tool call is the result of that conversation and consensus.

Q: Can AutoGen agents manage the entire lifecycle of a contact in FunnelCockpit?

Yes. You could have one agent for acquisition that uses createcontact. Another for nurturing that uses updatecontact to change tags. And a third for analysis that uses getcontact to build reports. They work together as a team.

Q: How does AutoGen handle the security of FunnelCockpit contact data during agent conversations?

The actual contact data from tools like getcontact is passed between agents within your controlled environment. The Vinkius MCP connection itself is encrypted and isolated, ensuring the data is only exposed to your specified agent group.

Let your AutoGen agent team debate and execute the best FunnelCockpit marketing strategy. Build consensus before acting.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FunnelCockpit MCP to AutoGen

Create your Vinkius account to connect FunnelCockpit 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 FunnelCockpit with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Marketing Strategy

Go beyond single-minded bots. With AutoGen, you can create a team of agents to manage your FunnelCockpit account. A "GrowthHacker" agent might propose a new campaign, using `list_funnels` to find a template. But then, a "DataAnalyst" agent can step in, call `get_funnel` to check the stats of similar funnels, and argue that a different approach is needed. The agents debate and converge on a plan before a single action is taken.

Debate and Execute Contact Updates

Modifying customer data is serious business. Instead of a single script blindly running `update_contact`, you can have a "Compliance" agent and an "Ops" agent discuss the change first. The Ops agent might propose an update based on new information. The Compliance agent can then use `get_contact` to check for GDPR consent flags before approving the `update_contact` call. It's a built-in sanity check.

Build a Self-Correcting Team with this MCP Server

AutoGen agents can work together to monitor and improve your funnels. One agent can periodically run `check_funnelcockpit_status` to ensure the API is healthy. Another can run `list_campaigns` and flag any that haven't had activity in 30 days. This isn't just automation; it's a conversation. The agents can discuss why a campaign is failing and propose solutions, like cloning a better-performing funnel structure found via `get_funnel`. This MCP server gives them the tools they need to act.

Setup guide

Set up FunnelCockpit 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 FunnelCockpit 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="FunnelCockpit_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

They talk it out. One agent might suggest using `create_contact`, but another might argue they need to `get_contact` first to avoid duplicates. The final tool call is the result of that conversation and consensus.

Absolutely. You can build a dedicated agent that does nothing but review proposed tool calls from other agents. It can check the parameters for `update_contact` or `create_contact` and "veto" the action if it violates your business rules.

A basic setup involves two agents: a UserProxy and an Assistant. You tell the UserProxy, "Find all funnels about our new product." The Assistant agent then uses the `list_funnels` tool and presents the results, starting a conversation about what to do next.

Yes. You could have one agent for acquisition that uses `create_contact`. Another for nurturing that uses `update_contact` to change tags. And a third for analysis that uses `get_contact` to build reports. They work together as a team.

The actual contact data from tools like `get_contact` is passed between agents within your controlled environment. The Vinkius MCP connection itself is encrypted and isolated, ensuring the data is only exposed to your specified agent group.

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