How to Use the Tray.io MCP in Google ADK

Q: What kind of data does this MCP Server handle for Tray.io and Google ADK?

It handles workflow meta-data, user details (getauthenticateduser), connection lists, and full execution logs, giving your agent a comprehensive view of the operational layer.

Q: What are the best practices for Tray.io and Google ADK integration?

We recommend using listavailableconnectors first to map out all endpoints. Then, use that inventory data in BigQuery models to predict future workflow needs.

Q: Is the user's identity secure when using Tray.io and Google ADK?

The server provides getauthenticateduser details. You must ensure your agent only accesses the specific fields required for its task, minimizing exposure of user identifiers.

Build Enterprise Agents with Google ADK. Run complex automations across Tray.io and BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tray.io MCP to Google ADK

Create your Vinkius account to connect Tray.io 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 Tray.io with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process Large Datasets via MCP Server

Your agent uses `list_integration_solutions` to discover all integration templates configured in the account. Because you're building enterprise agents, this discovery feeds directly into BigQuery queries. It allows your agent to map out existing data pipelines and plan complex multi-step actions across different services.

Monitor Automation History for Tray.io

If you need a full picture of what's been running, the `list_workflow_executions` tool pulls detailed records for specific automations. This execution data can then be loaded into BigQuery for long-context analysis. You get reliable historical metrics that go far beyond simple status checks.

Inventory All Workflows in Tray.io

The `list_workflows` tool gives your agent a complete list of every workflow available within the account structure. This lets the Gemini models reason over all possible automations. It's essential when building agents that need to choose between multiple operational paths based on business logic.

Setup guide

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

The MCP Server gives your agent the ability to list workflow details (`get_workflow_details`). These structured records can then be passed to BigQuery for long-context reasoning, letting Gemini models analyze patterns across your automations.

Yes. Since you're working on Google Cloud infrastructure, the agent can reliably connect to services like Vertex AI using data gathered from the available connectors list.

It handles workflow meta-data, user details (`get_authenticated_user`), connection lists, and full execution logs, giving your agent a comprehensive view of the operational layer.

We recommend using `list_available_connectors` first to map out all endpoints. Then, use that inventory data in BigQuery models to predict future workflow needs.

The server provides `get_authenticated_user` details. You must ensure your agent only accesses the specific fields required for its task, minimizing exposure of user identifiers.

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