How to Use the DeveloperHub MCP in Google ADK

Q: How do I set up the DeveloperHub MCP server with Google ADK?

You instantiate a single McpToolset object. Give it the server URL from Vinkius, then pass that toolset into the tools argument of your LlmAgent.

Q: How do I filter which DeveloperHub tools my Google ADK agent sees?

When you initialize your LlmAgent, use the toolnames filter. It lets you pass a list of exact function names from the MCP toolset that your agent is allowed to call, ignoring all others.

Connect Google ADK to your documentation. Let Gemini agents read, search, and monitor your DeveloperHub projects.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeveloperHub MCP to Google ADK

Create your Vinkius account to connect DeveloperHub 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 DeveloperHub with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Your Entire Doc Set to Gemini

Your agent can use `get_documentation_sitemap` to get a full map of a project, then iterate with `get_documentation_page_content` to pull everything into a Gemini agent's context window. Google ADK is built for this kind of large-scale analysis. You can analyze thousands of pages at once to find inconsistencies or generate summaries. This MCP integration is perfect for feeding your docs into a RAG pipeline on Vertex AI, letting your agent do the fetching and structuring.

Integrate Docs with GCP Data

Have your agent use `list_product_changelogs` to get the latest updates from DeveloperHub. With Google ADK, it can then cross-reference those changes with deployment logs in Google Cloud Logging or performance metrics in BigQuery. This closes the loop. You're not just reading docs anymore; you're connecting documentation events to real-world operational data inside your GCP environment.

Enterprise Search with your Google ADK MCP Server

Expose `search_documentation_portal` to a Gemini agent through the Google ADK. This lets your internal teams ask natural language questions and get answers sourced directly from your official DeveloperHub documentation. Since it's all running on Google Cloud, you can easily pipe the agent's output into other services. Have it post summaries to a Google Chat space or create a task for a technical writer.

Setup guide

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

You instantiate a single `McpToolset` object. Give it the server URL from Vinkius, then pass that toolset into the `tools` argument of your `LlmAgent`.

Yes, that's the whole point. The ADK is designed to combine toolsets. Your agent can pull a changelog from DeveloperHub with `list_product_changelogs` and then run a query in BigQuery in the very next step.

It's all about the tight integration with Google Cloud and Gemini's massive context window. You can build agents that reason over your entire DeveloperHub project and connect that information directly to your data living in BigQuery or Vertex AI.

When you initialize your `LlmAgent`, use the `tool_names` filter. It lets you pass a list of exact function names from the MCP toolset that your agent is allowed to call, ignoring all others.

The connection is specific to your DeveloperHub data. The agent will access documentation content, project lists, and changelogs. It doesn't see your Google Cloud credentials or other data unless you explicitly code it to. The Vinkius sandbox keeps the MCP server connection contained.

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