How to Use the Afosto MCP in Google ADK

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

You instantiate an McpToolset and pass your Vinkius server URL to StreamableHttpServerParameters. Then, you add this toolset to your LlmAgent's tools list. The ADK handles the connection to your Afosto endpoint.

Q: Can I use Google ADK to filter which Afosto tools are available?

Yes, the McpToolset constructor accepts a toolnames filter. You can provide a list of specific tool names, like 'listorders', 'listinventory', to restrict what the agent can do with your Afosto data via this MCP connection.

Q: Can my agent get Afosto customer data and analyze it with a Gemini model using Google ADK?

Absolutely. Your agent can call listcustomers to get the data from Afosto. Because Google ADK is built for Gemini, you can then pass that entire dataset into the model for sophisticated analysis, like identifying your most valuable customer segments.

Connect Afosto to your Google Cloud workflow with the Google Agent Development Kit.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Afosto MCP to Google ADK

Create your Vinkius account to connect Afosto 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 Afosto with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Correlate Orders with BigQuery Data

The `list_orders` tool pulls recent multi-channel orders directly from Afosto. Your agent gets the raw order data in a structured format. Here's the advantage of Google ADK: your agent can take that Afosto order data and natively cross-reference it with marketing campaign data you have stored in BigQuery. This lets you build agents that attribute sales directly to specific ads.

Analyze Inventory with Gemini Models

Use the `list_inventory` tool to get a complete snapshot of your stock levels across all warehouses from your Afosto account. With Google ADK, you can feed that entire inventory list into a Gemini model with a large context window. This allows your agent to perform complex analysis, like identifying slow-moving stock across your entire network. It's a unique strength of this MCP server when paired with Gemini.

Build Enterprise Agents on Your MCP Server

The `list_customers` and `list_products` tools expose your core Afosto e-commerce data. An agent can use this to build detailed customer profiles or generate product comparison reports. The Google ADK is designed for building agents that live inside your Google Cloud infrastructure. You can deploy an agent that monitors Afosto inventory and automatically triggers a re-ordering workflow in another GCP service.

Setup guide

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

You instantiate an `McpToolset` and pass your Vinkius server URL to `StreamableHttpServerParameters`. Then, you add this toolset to your `LlmAgent`'s `tools` list. The ADK handles the connection to your Afosto endpoint.

Yes, the `McpToolset` constructor accepts a `tool_names` filter. You can provide a list of specific tool names, like `['list_orders', 'list_inventory']`, to restrict what the agent can do with your Afosto data via this MCP connection.

If your business already runs on Google Cloud, it's the most direct path. The native integrations with BigQuery and Vertex AI mean your agent can combine Afosto e-commerce data with your other enterprise data sources without any extra glue code.

Absolutely. Your agent can call `list_customers` to get the data from Afosto. Because Google ADK is built for Gemini, you can then pass that entire dataset into the model for sophisticated analysis, like identifying your most valuable customer segments.

Your product catalog data is only accessed when an agent makes a specific request to the Afosto endpoint. The data flows through Vinkius's ephemeral, zero-trust environment, which manages authentication. The data itself isn't stored by Vinkius; it's just a proxy for your agent's call.

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