How to Use the GrowthBook MCP in OpenAI Agents SDK

Q: How do I connect the GrowthBook MCP Server to my OpenAI Agents SDK?

Install the package using pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass this server object in the mcpservers list when creating your Agent. Enable cacheToolsList=True to speed up tool discovery.

Q: Can my agent create new flags dynamically?

Yes, the agent calls createfeature to provision new flags. It handles the initial setup, including rules and default values, directly through the API.

Configure and toggle feature flags using the GrowthBook MCP Server with OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GrowthBook MCP to OpenAI Agents SDK

Create your Vinkius account to connect GrowthBook to OpenAI Agents SDK 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 GrowthBook with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Production-grade flag toggling via MCP Server

The `toggle_feature` tool changes your GrowthBook flag state instantly without code deployments. Your agent uses this to disable broken features in production or roll out new changes based on live performance metrics. By using this MCP Server with the OpenAI Agents SDK, you get built-in validation guardrails. If your agent tries to toggle a critical flag, the SDK intercepts the call, runs safety checks, and logs the execution trace directly to your OpenAI dashboard.

Dynamic environment configuration

The `create_environment` and `list_environments` tools handle the isolation of your staging and production flag configurations. Your agent reads these environments to verify where a flag is active before making any modifications. This setup lets you define specialized agents for different environments. A staging agent can safely use `update_environment` to test setups, while a production agent handles live traffic configs with tighter SDK guardrails.

Automated project isolation

The `create_project` and `list_projects` tools organize your feature flags into clean, team-specific boundaries. Your agent queries these projects to ensure it only modifies flags belonging to the target service. When your agent discovers new services, it uses `update_project` to keep your GrowthBook dashboard in sync. This prevents configuration drift across large engineering teams without manual dashboard clicking.

Setup guide

Set up GrowthBook MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all GrowthBook tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives GrowthBook tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate GrowthBook tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="GrowthBook Agent",
            instructions="You have access to GrowthBook tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 GrowthBook. 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 GrowthBook 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 GrowthBook MCP in OpenAI Agents SDK

Install the package using `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server object in the `mcp_servers` list when creating your Agent. Enable `cacheToolsList=True` to speed up tool discovery.

Yes, you configure this through the SDK's built-in guardrails and agent handoffs. You can route destructive tools like `delete_feature` to a highly restricted agent that requires human approval, while leaving `list_features` open for read-only agents.

The SDK relies on the server's HTTP responses to handle rate limiting. If `get_feature` hits GrowthBook API limits, the SDK catches the error, allowing your agent to retry the action or back off gracefully.

Yes, the agent calls `create_feature` to provision new flags. It handles the initial setup, including rules and default values, directly through the API.

Your GrowthBook flag payloads and project configurations stay secure within Vinkius's ephemeral V8 sandboxes. No configuration data is stored permanently on our servers; we act as a secure transit layer directly to your GrowthBook instance.

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