How to Use the VWO MCP in CrewAI

Q: Can I use CrewAI for listing goals when working with VWO?

Yes. You can give an 'Inventory' agent the listconversiongoals tool. This allows the crew to automatically build a master list of every tracked goal and metric.

Q: Does CrewAI help coordinate multiple VWO environments?

Absolutely. You can give an 'Ops' agent access to listvwoenvironments. This allows the crew to verify that a feature flag change is only attempted in the correct, designated environment.

Q: What happens if I need general VWO account info with CrewAI?

An 'Auditing' agent can use getvwoaccountinfo to pull baseline details about the VWO account. This initial data serves as shared memory for all subsequent, more complex tasks.

Build autonomous VWO operations using specialized agent teams with CrewAI.

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 CrewAI

Create your Vinkius account to connect VWO to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze specific campaign performance in VWO

Assign the `get_campaign_results` tool to an 'Analyst' agent. This agent researches the statistical outcomes for a given VWO test and compiles a summary report. The result is then passed to a separate 'Reporting' agent which formats it into actionable insights, all without human intervention.

Discover all available audience segments in VWO

Task the 'Discovery' agent with running `list_audience_segments`. This agent gathers every existing segment list from VWO. A subsequent 'Planning' agent then takes that full list and recommends which ones should be used for a new campaign, creating a cohesive plan.

Manage all VWO feature flags autonomously

Use the `toggle_feature_flag` tool within an agentic workflow. The 'Moderator' agent reviews the requested change and executes the toggle only after checking if the target environment is listed via `list_vwo_environments`. The CrewAI setup ensures that this decision-making process follows a strict, observable sequence.

Setup guide

Set up VWO MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke VWO tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="VWO Analyst",
    goal="Access and analyze VWO data via MCP.",
    backstory="Expert analyst with direct VWO access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent VWO transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="VWO Analyst",
        goal="Access and analyze VWO data via MCP.",
        backstory="Expert analyst with direct VWO access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent VWO transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

CrewAI assigns roles to agents: one researches the test using `get_campaign_details`, and another analyzes the retrieved data. The whole process runs autonomously, generating a complete report.

Yes. You can give an 'Inventory' agent the `list_conversion_goals` tool. This allows the crew to automatically build a master list of every tracked goal and metric.

Absolutely. You can give an 'Ops' agent access to `list_vwo_environments`. This allows the crew to verify that a feature flag change is only attempted in the correct, designated environment.

An 'Auditing' agent can use `get_vwo_account_info` to pull baseline details about the VWO account. This initial data serves as shared memory for all subsequent, more complex tasks.

This server touches operational configuration data, including campaign results and feature flag settings. It provides access to non-PII metadata about A/B tests.

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