How to Use the GrowthBook MCP in Google ADK

Q: How do I install the GrowthBook MCP Server in Google ADK?

First, run pip install google-adk in your environment. Next, initialize McpToolset with your Vinkius HTTP endpoint and pass it into the tools list of your LlmAgent.

Q: Can my agent toggle flags based on real-time alerts?

Yes, your agent can call togglefeature when an alert is triggered. It evaluates the live alert data and flips the flag to minimize downtime.

Control your GrowthBook MCP Server environments using Google ADK to automate rollouts.

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 Google ADK

Create your Vinkius account to connect GrowthBook to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context flag analysis with Google ADK

The `list_features` tool pulls your entire feature flag configuration into Gemini's massive one-million-token context window. Your agent analyzes thousands of active flags at once to find stale code or unused variations. Combining this MCP Server with the Google ADK allows your agent to cross-reference flag states with data stored in BigQuery. The agent checks if a flagged feature correlates with database errors and updates the flag state accordingly.

Automated feature flag cleanup

The `delete_feature` tool removes retired flags from your codebase once a rollout is complete. Your agent identifies flags that are 100% rolled out and deletes them to keep your dashboard clean. Using the Google ADK, you can filter tools using the `tool_names` parameter to keep this destructive action restricted. This ensures your agent only cleans up flags in specific sandbox projects.

Multi-environment synchronization

The `update_environment` and `list_environments` tools manage how flags behave across different deployment targets. Your agent uses them to sync flag rules between staging and production automatically. The Google ADK handles these complex multi-environment steps by running sequential LLM reasoning loops. It reads the source state, maps the differences, and updates the target environment without manual intervention.

Setup guide

Set up GrowthBook MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with GrowthBook tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="GrowthBook_agent",
    model="gemini-2.0-flash",
    instruction="You have access to GrowthBook tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

First, run `pip install google-adk` in your environment. Next, initialize `McpToolset` with your Vinkius HTTP endpoint and pass it into the `tools` list of your `LlmAgent`.

Yes, you can pass a list of allowed tool names to the toolset configuration. This prevents the agent from calling destructive tools like `delete_project` while allowing it to use `get_feature`.

The ADK works with Gemini's long-context window, meaning it easily processes massive payloads from `list_features` without truncation. The agent retains full context of all your flags and projects during complex reasoning tasks.

Yes, your agent can call `toggle_feature` when an alert is triggered. It evaluates the live alert data and flips the flag to minimize downtime.

All feature rules and project definitions are processed in zero-trust, isolated containers. Your API tokens are encrypted at rest, and we never inspect or cache the flag payloads passing through the server.

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