How to Use the VWO MCP in AutoGen

Q: How does VWO account info work with AutoGen?

You can feed getvwoaccountinfo into a multi-agent debate. For instance, one agent confirms the scope of the account while another agent verifies if that scope is sufficient for the requested action.

Q: What metrics are tracked by VWO using AutoGen?

The server tracks clicks and revenue goals via listconversiongoals. You can set up agents to challenge each other's interpretation of which goal is most valuable, reaching a consensus on priority.

Q: Can I manage feature flags with VWO and AutoGen?

Yes. The agent uses togglefeatureflag but first runs it through a 'Policy Agent' that debates whether the change violates any internal rules, ensuring responsible deployment.

Q: How are VWO environments managed with AutoGen?

When listing environments via listvwoenvironments, you can have agents debate which environment is the safest place to run a test—Production vs. Staging—before any action is taken.

Q: If I need campaign details, how does VWO expose that with AutoGen?

The agent calls getcampaigndetails, and then two agents debate the meaning of those details: one focuses on technical specs, while the other translates it into business impact. You get both perspectives.

Debate A/B test strategies with AutoGen using VWO's tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VWO MCP to AutoGen

Create your Vinkius account to connect VWO 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 VWO with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Review campaign results through debate.

Start by having the agent call `get_campaign_results` to gather performance metrics. You can then set up two agents—one 'Performance Analyst' and one 'Budget Watchdog'—to argue over which result is most actionable. The consensus on the outcome emerges from their debate, giving you a nuanced recommendation that simple data retrieval misses.

Determine feature flag status by deliberation.

Want to know if a flag should be enabled? The agent first uses `get_feature_flag_details` and then has 'Risk Agent' and 'Launch Agent' debate the implications of setting it to true or false. They challenge each other's assumptions. The final, agreed-upon decision is presented to you, mitigating the risk of a single point of failure in logic.

Inventory all optimization tests.

Use `list_optimization_campaigns` to pull every active test into the conversation. Then, have one agent list the campaign IDs and another cross-reference those IDs with `get_campaign_details`. The debate converges on a complete, verified inventory. This approach ensures that no running campaign is missed because multiple agents verify the data points.

Setup guide

Set up VWO 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 VWO 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="VWO_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You can feed `get_vwo_account_info` into a multi-agent debate. For instance, one agent confirms the scope of the account while another agent verifies if that scope is sufficient for the requested action.

The server tracks clicks and revenue goals via `list_conversion_goals`. You can set up agents to challenge each other's interpretation of which goal is most valuable, reaching a consensus on priority.

Yes. The agent uses `toggle_feature_flag` but first runs it through a 'Policy Agent' that debates whether the change violates any internal rules, ensuring responsible deployment.

When listing environments via `list_vwo_environments`, you can have agents debate which environment is the safest place to run a test—Production vs. Staging—before any action is taken.

The agent calls `get_campaign_details`, and then two agents debate the meaning of those details: one focuses on technical specs, while the other translates it into business impact. You get both perspectives.

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