How to Use the Avaza MCP in Google ADK

Q: Can Google ADK filter which Avaza tools the agent uses?

Yes. You can apply a toolnames filter to your toolset configuration. This prevents the agent from calling endpoints like createproject if it should only have read access.

Q: Does Google ADK support creating Avaza tasks?

The framework maps the createtask tool directly to the Gemini model. Your agent can generate new work items based on its long-context reasoning of your project data.

Q: How do I verify the MCP Server is working?

Run the getaccountcheck tool before executing complex workflows. This confirms the Vinkius endpoint is active and authenticated.

Give your Google ADK agents native access to Avaza projects, tasks, and timesheets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Avaza MCP to Google ADK

Create your Vinkius account to connect Avaza 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 Avaza with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Avaza Data into Google ADK Context

Gemini models can hold over a million tokens, which means you can dump massive amounts of project history right into the prompt. Connect the Avaza MCP Server and let your agent run `list_projects` followed by multiple `get_project` calls. The agent absorbs the entire state of your professional services organization. From there, it can cross-reference that live data with historical records you already keep in BigQuery.

Manage Tasks from Vertex AI

Building enterprise agents requires tools that actually change state. You configure a McpToolset with your Vinkius URL, and suddenly your Gemini agent can execute `create_task` and `update_task` directly. You dictate exactly which operations are allowed using the tool_names filter. If you only want the agent to assign work, restrict it to those specific task endpoints and block everything else.

Sync Timesheets and Invoices

Tracking billable hours across a large team is notoriously difficult. Your Google Cloud agent can pull active records using `list_timesheets` and `list_invoices` to audit missing entries. When it finds a gap, the agent can generate a new entry via `create_timesheet`. You get accurate billing without forcing developers to manually log into a separate dashboard.

Setup guide

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

Install google-adk and initialize a McpToolset using the StreamableHttpServerParameters class. Pass that toolset to your LlmAgent and it will map the endpoints automatically.

Yes. You can apply a tool_names filter to your toolset configuration. This prevents the agent from calling endpoints like create_project if it should only have read access.

The framework maps the create_task tool directly to the Gemini model. Your agent can generate new work items based on its long-context reasoning of your project data.

Run the get_account_check tool before executing complex workflows. This confirms the Vinkius endpoint is active and authenticated.

Vinkius processes all requests in an isolated V8 sandbox. When your agent reads financial records, the execution environment is destroyed immediately after the response is sent.

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