How to Use the Axonaut MCP in Google ADK

Q: How do I use the Axonaut MCP Server with Google ADK?

Install the google-adk package. Initialize an McpToolset with your Vinkius endpoint parameters, then pass that toolset into your LlmAgent setup.

Q: Can Google ADK read Axonaut product lists?

The listproducts tool pulls your entire catalog into the agent's context. Gemini can then use that data to answer questions about pricing or availability.

Q: How do I limit which Axonaut tools the agent can see?

Use the toolnames filter when setting up the toolset. This prevents the agent from seeing createtask if you want a strictly read-only implementation.

Connect Axonaut to Google ADK to let Gemini analyze your CRM contacts and invoices alongside BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Axonaut MCP to Google ADK

Create your Vinkius account to connect Axonaut 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 Axonaut with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise MCP Server analytics

Feeding CRM numbers into Gemini's massive context window changes how you handle reporting. Your code can execute `list_invoices` and `list_expenses` to dump raw financial histories directly into the model's memory. Google Cloud infrastructure handles the scale. The agent takes those Axonaut records and cross-references them against whatever you have sitting in Vertex AI or BigQuery.

Project and order tracking

Keeping tabs on active work requires constant polling. You can configure your `LlmAgent` to run `list_projects` and `list_orders` on a schedule. Filtering exposed operations keeps the agent focused. If you only want it monitoring status, use the `tool_names` parameter in your `McpToolset` to restrict access strictly to those read tools.

Automated task generation

Finding bottlenecks in your pipeline is useless if you do not act on them. Once Gemini identifies a stalled account via `get_company`, it triggers `create_task` to assign a follow-up. Connection happens over HTTP or Stdio transports depending on your deployment. Just pass the Vinkius URL into `StreamableHttpServerParameters` and the agent handles the rest.

Setup guide

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

Install the `google-adk` package. Initialize an `McpToolset` with your Vinkius endpoint parameters, then pass that toolset into your `LlmAgent` setup.

The `list_products` tool pulls your entire catalog into the agent's context. Gemini can then use that data to answer questions about pricing or availability.

Long context is exactly what makes this powerful. You can pull hundreds of records using `list_quotations` and `list_companies`, and Gemini will process the entire batch without losing details.

Use the `tool_names` filter when setting up the toolset. This prevents the agent from seeing `create_task` if you want a strictly read-only implementation.

Auth happens through a single endpoint token rather than passing raw credentials. Whenever your agent reads quotes or order histories, the transaction occurs inside a zero-trust execution boundary that destroys itself after the run.

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