How to Use the ActiveTrail MCP in AutoGen

Q: How do I expose ActiveTrail to my AutoGen agents?

Install the autogen-extmcp package. Pass your Vinkius MCP endpoint URL into mcpservertools, and hand the resulting tool list to your AssistantAgent constructor.

Deploy debating AutoGen agents that analyze segments and execute ActiveTrail campaigns via consensus.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ActiveTrail MCP to AutoGen

Create your Vinkius account to connect ActiveTrail 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 ActiveTrail with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent campaign strategy

Marketing decisions rarely happen in a vacuum. You spin up a copywriter agent and a compliance agent to debate the contents of a new message. They pull active lists via the MCP connection using the `list_campaigns` tool to see what worked previously. The agents argue over the right approach until they reach an agreement. Once consensus hits, the executor agent takes over and formats the final output for delivery. You get automated strategy backed by actual data.

Negotiated audience targeting via MCP Server

Picking the wrong segment wastes money. Your data analyst agent calls the MCP tool `list_groups` to retrieve available cohorts. A budget agent reviews the sizes and pushes back if the list looks too expensive to hit. Retrieving the exact user base takes one call to `list_contacts`. The agents parse the directory together, filtering out bad fits before anyone touches the send button. This prevents costly broadcast mistakes.

Supervised SMS execution

Firing off immediate texts requires strict oversight. One agent drafts the notification while a separate security agent verifies the phone numbers. The `send_sms` tool only fires when both parties approve the payload. Adding new subscribers demands similar rigor. A validation agent checks the input format before passing it to `create_contact` for insertion. Errors get caught during the conversation phase, keeping your database clean.

Setup guide

Set up ActiveTrail 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 ActiveTrail 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="ActiveTrail_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Pass your Vinkius MCP endpoint URL into `mcp_server_tools`, and hand the resulting tool list to your `AssistantAgent` constructor.

They handle it entirely on their own. The agents call the directory tools, read the JSON responses, and share the findings in their chat history.

No. The MCP tool adapter converts the server schemas automatically. Your agents read the requirements and construct the correct JSON arguments during their internal dialogue.

Require a human-in-the-loop for the execution agent. The system will pause and ask for your approval in the terminal before firing the SMS tool.

We isolate every connection in a hardened V8 sandbox. When your agents debate over personal details and email addresses, the data passes through a single-use token endpoint and leaves no trace on our infrastructure.

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