How to Use the Viral Loops MCP in AutoGen

Q: How do I get all my campaign options with Viral Loops and AutoGen?

You start by using listcampaigns. This output provides a list of IDs that your agents can then feed into the getcampaign tool to gather full context.

Q: Can AutoGen help decide on optimal rewards for Viral Loops?

Yes. Agents debate potential changes by calling getrewards and comparing those results against current milestone performance via getmilestones.

Q: What are the key functions for managing participants in AutoGen?

The system provides tools like createparticipant, which adds new users, and listparticipants, useful for an agent needing to run a leaderboard analysis.

Run consensus-driven decision making across Viral Loops 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 Viral Loops MCP to AutoGen

Create your Vinkius account to connect Viral Loops 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 Viral Loops with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

MCP Server: Campaign Discovery and Review

Multiple agents can debate which campaign to optimize. One agent might list all options using `list_campaigns`, while a second calls `get_campaign` for deep context. They negotiate on the best starting point before any changes are made.

Formulating Strategy with AutoGen

Agents can collaborate to design rewards. One agent checks existing rules using `get_rewards`, and a second suggests an improvement based on observed goals from `get_milestones`. The conversation converges on the best proposed reward structure.

Managing Participants via AutoGen

Agents can handle user management through debate. An agent might identify a new participant using `create_participant` based on a form submission, and another agent runs `get_referral_url` to ensure the link is ready for use.

Setup guide

Set up Viral Loops 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 Viral Loops 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="Viral Loops_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You start by using `list_campaigns`. This output provides a list of IDs that your agents can then feed into the `get_campaign` tool to gather full context.

Yes. Agents debate potential changes by calling `get_rewards` and comparing those results against current milestone performance via `get_milestones`.

Agents can manage this flow. One agent identifies the participant via email (`get_participant`), and another executes `update_participant` with the approved changes.

The system provides tools like `create_participant`, which adds new users, and `list_participants`, useful for an agent needing to run a leaderboard analysis.

This MCP Server handles participant records. The specific data types include the user's email address, their campaign ID, and any associated referral URL data.

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