How to Use the Flagsmith MCP in Google ADK

Q: How do I connect the Flagsmith MCP Server to a Google ADK agent?

Install the package via pip install google-adk. Create an instance of McpToolset using StreamableHttpServerParameters pointing to your Vinkius URL, then pass it to your LlmAgent in the tools parameter.

Q: Can I limit which Flagsmith tools are exposed to my Google ADK agent?

Yes, you can use the optional toolnames filter when initializing your McpToolset. This allows you to expose read-only tools like getenvironmentflags while hiding destructive tools like deletesegmentoverride.

Q: How are my Flagsmith credentials protected in Google ADK?

Your FLAGSMITHAPIKEY and environment configurations are injected as secure environment variables. Vinkius executes the MCP Server within an ephemeral V8 sandbox, preventing any token leakage or persistence of sensitive configuration payloads.

Manage Flagsmith environments and user overrides using Gemini long-context reasoning in the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flagsmith MCP to Google ADK

Create your Vinkius account to connect Flagsmith 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 Flagsmith with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Expose Flagsmith MCP Server tools to Google ADK

The `get_environment_document` tool pulls down your entire environment state so Gemini can analyze it within its million-token context window. This tool provides the raw configuration document that your agent needs to understand complex targeting rules. Because the Google ADK supports deep reasoning over MCP, your agent can cross-reference this document with user telemetry stored in BigQuery. It makes smart decisions about which segments are performing best without hitting API rate limits.

Modify targeting rules on the fly with Google ADK

The `delete_segment_override` tool removes custom rules for specific user segments instantly. This tool lets your agent clean up temporary marketing campaigns or emergency hotfixes without manual intervention. Your agent coordinates this cleanup by running background tasks in Vertex AI. It evaluates performance metrics and automatically triggers the deletion tool when a feature rollout reaches one hundred percent.

Provision new environments for serverless pipelines

The `create_environment` tool spins up isolated testing environments programmatically using your Flagsmith API key. This tool allows your agent to prepare clean environments for automated testing pipelines. The Google ADK handles this setup during CI/CD runs. By combining this tool with Google Cloud triggers, your agent provisions, tests, and tears down feature flag environments automatically.

Setup guide

Set up Flagsmith 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 Flagsmith 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="Flagsmith_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Flagsmith 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 Flagsmith. 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 Flagsmith 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 Flagsmith MCP in Google ADK

Install the package via `pip install google-adk`. Create an instance of `McpToolset` using `StreamableHttpServerParameters` pointing to your Vinkius URL, then pass it to your `LlmAgent` in the tools parameter.

Yes, you can use the optional `tool_names` filter when initializing your `McpToolset`. This allows you to expose read-only tools like `get_environment_flags` while hiding destructive tools like `delete_segment_override`.

The agent queries BigQuery for user behavior trends, then uses `update_flag_v2` to adjust feature availability based on those insights. This creates a closed-loop system where data directly drives your product configuration.

Yes, the Google ADK supports both Stdio and HTTP transports. While Vinkius provides managed MCP endpoints, you can run the server locally over stdio during development before deploying to Google Cloud.

Your `FLAGSMITH_API_KEY` and environment configurations are injected as secure environment variables. Vinkius executes the MCP Server within an ephemeral V8 sandbox, preventing any token leakage or persistence of sensitive configuration payloads.

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