How to Use the Ayanza MCP in Google ADK

Q: How do I register the Ayanza toolset in Google ADK?

Use McpToolset with your HTTP server parameters pointing to the Vinkius URL. Pass this toolset into your LlmAgent constructor. The agent automatically discovers tools like listtasks and makes them available for LLM function calling.

Q: Can a Google ADK agent update an Ayanza task based on Vertex AI logs?

Yes, the agent triggers updatetask when specific log patterns appear in Vertex AI. You write the orchestration logic in Python, and the model decides when to invoke the tool. This connects your live system monitoring directly to your project board.

Feed Ayanza workspace data directly into Google ADK agents to power long-context reasoning with Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ayanza MCP to Google ADK

Create your Vinkius account to connect Ayanza 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 Ayanza with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Ayanza to Google ADK for enterprise analysis

Exposing tools like `list_wiki_pages` and `list_projects` to Gemini's million-token context window allows your agent to analyze entire project histories in one go. You don't have to worry about running out of memory when pulling deep documentation. The setup requires importing `McpToolset` from the Google ADK library. You pass your Vinkius HTTP endpoint into the parameters, and the agent instantly maps the tool definitions. This lets you run complex analytical prompts across all your workspace databases.

Cross-reference BigQuery datasets with this MCP Server

This MCP Server bridges the gap between databases by letting your Google ADK agent run `update_task` based on BigQuery thresholds. It executes `update_task` based on actual database thresholds. If a data pipeline fails, the agent detects the anomaly in Vertex AI. It immediately runs `get_task` to check the current status of the on-call engineer's ticket. When necessary, it modifies the priority level without human intervention.

Automate task creation from Vertex AI events

Configuring `create_task` within your agent's toolkit allows Gemini to write detailed bug reports based on system logs. The model extracts the stack trace and formats the ticket automatically. Use the optional `tool_names` filter to limit what the agent can do. This ensures a monitoring agent can only write tasks, leaving destructive actions like `delete_task` completely blocked. Your system stays secure while automating the boring stuff.

Setup guide

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

Use `McpToolset` with your HTTP server parameters pointing to the Vinkius URL. Pass this toolset into your `LlmAgent` constructor. The agent automatically discovers tools like `list_tasks` and makes them available for LLM function calling.

Yes, the agent triggers `update_task` when specific log patterns appear in Vertex AI. You write the orchestration logic in Python, and the model decides when to invoke the tool. This connects your live system monitoring directly to your project board.

Gemini models handle up to two million tokens, allowing the agent to ingest multiple documents retrieved via `list_wiki_pages`. The agent reads entire wiki structures to answer complex questions without losing context. This makes workspace search highly accurate.

The integration supports both Stdio and HTTP transport mechanisms. For hosted production agents on Google Cloud, the HTTP transport is recommended. It connects directly to your Vinkius-managed MCP Server endpoint.

All communication between Google Cloud and the Vinkius sandbox is encrypted using TLS. Your personal Ayanza credentials, workspace IDs, and task titles are never stored on intermediate servers. The runtime environment is completely ephemeral and isolates your data.

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