How to Use the VWO MCP in LangChain

Q: How do I check VWO account info using LangChain?

Just call getvwoaccountinfo. It pulls all the basic details about the authenticated VWO account and spits that data right into your chain's memory. You can then use that information for subsequent steps.

Q: Does VWO support feature flag management with LangChain?

Yes. The togglefeatureflag function lets your agent enable or disable any flag. You provide the ID and whether it needs to be true or false for the action.

Q: If I need campaign results, how does VWO expose that data using LangChain?

You retrieve statistical performance by calling getcampaignresults. You only need the specific campaign ID; the tool handles pulling all the relevant metrics for you.

Build multi-step A/B testing flows with LangChain.

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 LangChain

Create your Vinkius account to connect VWO to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage campaign details in a chain.

Start by calling `get_campaign_details` to pull up the specs for any VWO test. This output then feeds directly into another step, maybe checking the associated goals using `list_conversion_goals`. You build these pipelines because you don't want to manually copy data between tabs. Your agent executes a full workflow—from finding campaign IDs to confirming their status.

Toggle feature flags across environments.

The chain starts by listing all available flag configurations using `list_feature_flags` and checking which environment you're in via `list_vwo_environments`. Next, the agent calls `toggle_feature_flag`, passing both the necessary ID and the desired 'true' or 'false' status. This ensures that if your flow requires enabling a flag before proceeding to test results, it handles the state change automatically, maintaining context throughout.

List all optimization campaigns.

You need an overview of everything running? The agent calls `list_optimization_campaigns` to get every active A/B test and personalization effort. That list is then passed to a subsequent step, which might use the IDs found there to call `get_campaign_results`. This allows you to build a single chain that first inventories all options, and then drills down into the performance metrics for specific groups.

Setup guide

Set up VWO MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes VWO tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "vwo-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent VWO transactions"
    })
    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 LangChain

Just call `get_vwo_account_info`. It pulls all the basic details about the authenticated VWO account and spits that data right into your chain's memory. You can then use that information for subsequent steps.

The server tracks multiple types of metrics, including specific click counts and revenue totals. You access these via the `list_conversion_goals` tool, which tells you exactly what is being measured.

Yes. The `toggle_feature_flag` function lets your agent enable or disable any flag. You provide the ID and whether it needs to be true or false for the action.

You can list all configured environments—like Production or Staging—using `list_vwo_environments`. This is crucial because it lets your agent know where to execute the feature flag changes.

You retrieve statistical performance by calling `get_campaign_results`. You only need the specific campaign ID; the tool handles pulling all the relevant metrics for you.

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