How to Use the GrowthBook MCP in AutoGen

Q: How do I register GrowthBook tools with AutoGen agents?

Install autogen-extmcp and use the mcpservertools adapter with your server URL. Pass the resulting tool list to your AssistantAgent constructor so the agent can call tools like togglefeature.

Q: How do AutoGen agents manage multiple GrowthBook environments?

The agents use listenvironments to map out your infrastructure. They then coordinate sequential rollouts, ensuring a flag is toggled in staging before proposing a production toggle.

Q: Can I limit which AutoGen agents have access to destructive tools?

Yes, you can register tools like deleteproject only with your highly constrained admin agent, while leaving read-only tools available to the rest of the group.

Let AutoGen agents debate and approve GrowthBook feature releases before toggling them in production.

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 AutoGen

Create your Vinkius account to connect GrowthBook 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 GrowthBook with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate feature rollouts with AutoGen agents

The `toggle_feature` tool is governed by collaborative agent workflows that require consensus before modifying production states. A developer agent can propose enabling a flag, but a security agent must review the configuration before the action is executed. This multi-agent debate prevents accidental rollouts of untested code. Once both agents agree that the deployment criteria are met, the MCP Server executes the toggle command and updates your environment instantly.

Coordinate multi-project setups

The `create_project` tool allows your AutoGen coordination agent to establish new workspaces when a team requests a sandbox. Different specialized agents handle naming conventions, access controls, and default settings during the setup process using our MCP Server. By calling `create_environment` alongside project creation, the agents ensure that every new workspace has staging and production targets pre-configured. This automated provisioning keeps your organizational structure uniform across all teams.

Audit flag hygiene via cooperative agents

The `list_features` tool provides the raw audit data that your compliance and engineering agents analyze for technical debt. One agent scans for flags older than thirty days, while another checks if those flags are fully rolled out. If a flag is deemed stale, the agents negotiate whether to archive it, eventually calling `delete_feature` to clean up the workspace. This cooperative housekeeping ensures your GrowthBook instance remains highly organized without manual oversight.

Setup guide

Set up GrowthBook 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 GrowthBook 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="GrowthBook_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent GrowthBook 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 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 AutoGen

Install autogen-ext[mcp] and use the mcp_server_tools adapter with your server URL. Pass the resulting tool list to your AssistantAgent constructor so the agent can call tools like `toggle_feature`.

Yes, if an agent fails to update a flag due to a version mismatch, the group chat manager can route the failure to a resolver agent. That agent calls `get_feature` to fetch the latest state and merges the updates.

The agents use `list_environments` to map out your infrastructure. They then coordinate sequential rollouts, ensuring a flag is toggled in staging before proposing a production toggle.

Yes, you can register tools like `delete_project` only with your highly constrained admin agent, while leaving read-only tools available to the rest of the group.

Yes, all agent conversations and tool executions occur within your private network or local runtime. The Vinkius MCP integration uses ephemeral tokens to query your GrowthBook API, keeping your project structures and active flag payloads completely isolated.

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