How to Use the Audienceful MCP in AutoGen

Q: How do I configure Audienceful MCP tools for AutoGen agents?

Install autogen-extmcp and use mcpservertools with StreamableHttpServerParams. The McpToolAdapter converts the schema automatically for your AssistantAgent constructor.

Q: What happens if an AutoGen agent tries to delete an Audienceful custom field?

If granted access to deletecustomfield, the agent will execute it. You should set up a reviewer agent to challenge destructive actions before they run.

Deploy AutoGen agents that debate marketing strategies and execute Audienceful campaigns based on consensus.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Audienceful MCP to AutoGen

Create your Vinkius account to connect Audienceful 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 Audienceful with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Audienceful MCP Server Control

The Audienceful MCP Server allows your AutoGen assistants to manage email lists through collaborative negotiation. A data-cleaning agent suggests removing inactive users via `delete_person`, while a retention agent argues to run `trigger_automation` instead. Reaching a decision requires data, which they gather by debating the output of `list_send_reports`. Once the agents agree on the best approach, the designated executor applies the changes directly to the marketing platform.

Consensus-Driven Subscriber Updates

Modifying user profiles happens only after competing perspectives align. One agent monitors external purchase data and proposes an `update_person` call, while another verifies the format using `list_custom_fields`. If a required attribute is missing, the system does not just fail. The agents discuss the error, agree on the necessary schema, and execute `create_custom_field` before retrying the original profile update.

Collaborative List Building

Onboarding new users involves multiple checks before executing `create_person`. A compliance agent ensures the email address is valid, while a marketing agent assigns the correct tags based on the acquisition source. Finding existing records prevents duplicates during this process. The team queries `list_people` to check for prior history, and if a match exists, they fetch the full profile using `get_person` to merge the new data.

Setup guide

Set up Audienceful 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 Audienceful 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="Audienceful_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use `mcp_server_tools` with `StreamableHttpServerParams`. The `McpToolAdapter` converts the schema automatically for your `AssistantAgent` constructor.

You pass the tool list to specific agents in your group chat. A planning agent might have read-only access, while only the executor agent holds permission to modify records.

They debate the timing and audience segment first. Once consensus is reached, the executor calls `trigger_automation` for the specific subscriber UID.

If granted access to `delete_custom_field`, the agent will execute it. You should set up a reviewer agent to challenge destructive actions before they run.

Vinkius isolates the execution environment entirely. Names, email addresses, and custom field values exist only in memory during the conversation, disappearing completely once the multi-agent session terminates.

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