How to Use the Bexio MCP in Google ADK

Q: How do I initialize the Bexio toolset inside the Google ADK?

You start by running pip install google-adk in your environment. Then, instantiate McpToolset using StreamableHttpServerParameters pointing to your Vinkius URL, and pass it directly to your LlmAgent tools array.

Connect Gemini to your Swiss ERP using the Google ADK and act on business data instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bexio MCP to Google ADK

Create your Vinkius account to connect Bexio 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 Bexio with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Context-rich ERP reasoning via Google ADK

Gemini's massive context window lets you feed thousands of rows of business data directly into your agent's memory using `list_orders` or `list_projects`. This capability allows the model to find deep patterns across your entire business history over MCP. Your Google ADK agent can cross-reference active projects against open invoices to flag clients who are behind on payments.

Restrict agent access using this MCP Server tool filtering

Giving an agent access to your entire accounting system is risky, but you can restrict it by filtering the tools exposed by this MCP Server. You can restrict a customer support agent to only use `list_contacts` and `get_contact`. This ensures the agent cannot touch `list_invoices` or read sensitive salary details from `list_users`.

Enterprise data pipelines with BigQuery and Bexio

If you keep your data warehouse on Google Cloud, you can merge live Swiss business data with cold storage metrics by calling `list_items` directly from your agent. The ADK coordinates these steps natively. Your LLM agent acts as the decision engine, pulling from the live MCP Server and writing structured summaries back to your cloud database.

Setup guide

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

You start by running `pip install google-adk` in your environment. Then, instantiate `McpToolset` using `StreamableHttpServerParameters` pointing to your Vinkius URL, and pass it directly to your `LlmAgent` tools array.

Yes, you can use the optional tool filter parameter in the ADK toolset configuration. This lets you expose only safe tools like `list_items` while completely hiding sensitive writing tools like `create_contact`.

The SDK supports both transport types out of the box. For managed cloud deployments, you will want to use the streamable HTTP transport provided by Vinkius to connect your Gemini models to the MCP Server.

Because Gemini models feature massive context windows, your agent can ingest the entire output of `list_invoices` without running out of memory. This makes it easy to run complex financial summaries over thousands of lines.

All communications between Gemini and your Swiss ERP data—including contacts, orders, invoices, and projects—occur over encrypted HTTPS channels. Vinkius runs the connector in a zero-trust, ephemeral sandbox that never caches your financial statements or customer lists.

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