How to Use the LaunchDarkly MCP in Google ADK

Q: Can I restrict tools for my Google ADK agent?

Absolutely. Use the toolnames filter when initializing your McpToolset. It prevents your agent from accessing tools you don't want it to run.

Q: How do I check LaunchDarkly projects with Google ADK?

Call listprojects to get the list of available project keys. Your agent uses this to set the scope for subsequent flag or metric queries.

Connect your Google ADK agents to LaunchDarkly to manage feature releases across your infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LaunchDarkly MCP to Google ADK

Create your Vinkius account to connect LaunchDarkly 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 LaunchDarkly with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Access LaunchDarkly flags using Google ADK

Your agent interacts with flag configurations via `get_feature_flag` to adjust system behavior on the fly. It fits into your Google Cloud agent logic by treating flags as standard tool inputs. Use `list_feature_flags` to inventory your current toggle set. It allows your agent to map out the available feature surface area before it makes any runtime adjustments.

Monitor deployments with this MCP Server

Your agent pulls recent history using `list_audit_logs` to verify the impact of recent changes. It keeps your Google ADK agent aware of who modified the state and why. Getting this data directly into your agent flow means faster debugging. You stop jumping between consoles and start letting the agent correlate flag changes with your system logs.

Verify environment state in Google ADK

Check your target environment using `list_environments` to ensure your agent is operating on the correct production or staging bucket. It reduces the chance of cross-environment drift. Calling `get_environment` gives your agent the context it needs to safely navigate your infrastructure. It ensures every decision the agent makes is scoped to the right deployment environment.

Setup guide

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

Initialize an McpToolset with your server URL and pass it to your LlmAgent. Your agent will have immediate access to all nine LaunchDarkly tools.

Yes. Your agent can ingest entire lists of flags or audit logs into its context window. It makes complex flag management tasks much easier to reason through.

Absolutely. Use the tool_names filter when initializing your McpToolset. It prevents your agent from accessing tools you don't want it to run.

Call `list_projects` to get the list of available project keys. Your agent uses this to set the scope for subsequent flag or metric queries.

The server only reads your audit logs through the defined MCP interface. It does not store or leak your configuration history, ensuring your internal deployment details remain private.

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