How to Use the DevCycle MCP in Google ADK

Q: How do I register the DevCycle MCP Server with Google ADK?

Install the google-adk package. Define an McpToolset using StreamableHttpServerParameters pointing to your Vinkius URL. Pass that toolset directly into the tools array of your LlmAgent.

Q: Does Google ADK support filtering DevCycle tools?

Yes. You can use the toolnames filter in the ADK setup. This lets you restrict a specific agent to just listactiveflags while blocking write access entirely.

Q: How does the agent know which environment to target?

It queries listprojectenvironments to get the exact IDs. You can prompt the agent to always verify the environment name matches 'Staging' before it executes any changes.

Connect DevCycle to your Google ADK agents to manage feature flags across massive BigQuery datasets and Gemini contexts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevCycle MCP to Google ADK

Create your Vinkius account to connect DevCycle 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 DevCycle with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cross-Reference Flags with BigQuery

Enterprise environments do not operate in silos. Your Google ADK agent can pull user cohorts from BigQuery and instantly check their access via `get_feature_flag_details`. It cross-references your internal analytics with live DevCycle targeting rules in one continuous reasoning loop. Gemini's massive context window changes how you audit. You can dump the entire output of `list_feature_flags` and `list_feature_variables` into the prompt. The agent digests your entire routing logic at once, spotting conflicting rules across hundreds of active variations.

Manage Environments with this MCP Server

Your agent needs exact SDK keys to configure downstream services. It calls `get_environment_sdk_keys` and injects those directly into your Vertex AI pipelines. No manual copying from the DevCycle dashboard. When spinning up new test infrastructure, the agent verifies the target exists using `list_project_environments`. If it needs to isolate a specific release, it runs `search_feature_flags` to find the exact toggle and applies the required state.

Autonomous Release Operations

You build agents to do the heavy lifting. When an anomaly triggers an alert in Google Cloud, your agent investigates. It identifies the offending feature via `list_active_flags` and immediately fires `update_feature_flag_status` to kill it. It never guesses the project structure. The agent maps the hierarchy by calling `list_devcycle_projects` followed by `get_project_details`. It knows exactly which environment it's touching before it alters any state.

Setup guide

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

Install the `google-adk` package. Define an `McpToolset` using `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass that toolset directly into the `tools` array of your `LlmAgent`.

Yes. You can use the `tool_names` filter in the ADK setup. This lets you restrict a specific agent to just `list_active_flags` while blocking write access entirely.

That is exactly what this does. You can gate specific LLM features or prompt variations behind DevCycle flags. Your agent reads `get_feature_flag_details` to determine which model version to serve to specific user segments.

It queries `list_project_environments` to get the exact IDs. You can prompt the agent to always verify the environment name matches 'Staging' before it executes any changes.

Authentication happens at the infrastructure layer. You provide one endpoint token, and the managed MCP Server handles the DevCycle API credentials securely. The agent sees your variation data and rule sets, but the execution environment is destroyed immediately after the session ends.

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