How to Use the Structured MCP in Google ADK

Q: How does google-adk list all structured plans?

You instruct the agent to call listplans. This tool returns a complete manifest of every plan, which your Gemini model can then ingest and process against other BigQuery data.

Q: Can I programmatically create tasks using google-adk?

Absolutely. By calling createtask with a title and optional start time, you let your agent build new entries directly into Structured for immediate tracking.

Q: What user data is available to my agents via google-adk?

The server exposes the current user profile through getuserprofile. Your agent can use this tool to verify identity and scope before performing write operations on Structured.

Q: Which tools are best for managing structured data with google-adk?

Use listtasks first to see everything. Then, if you need to make a change, use updatetask. This two-step process is clean and reliable for maintaining data integrity.

Write enterprise agents on Google Cloud using google-adk to act on Structured data in BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Structured MCP to Google ADK

Create your Vinkius account to connect Structured to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Structured with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Plan Management for Scale

Your agent can access and manage project planning by calling `list_plans` or fetching a single plan's full context using `get_plan_details`. This is perfect when you need to feed structured data into BigQuery for analysis. The integration handles the heavy lifting of retrieving multiple plans, giving your Gemini model enough initial context to run complex, multi-step reasoning across different projects.

Task Lifecycle Control

Need to modify a task? Use `update_task` for changes, or use `create_task` if the goal is new tracking. The agent handles this entire lifecycle flow—from creation to modification—all through Google Cloud services. You can also confirm deletion using `delete_task`, which gives your agent the necessary final confirmation step before executing irreversible actions.

User & Task Context Retrieval

Before making a decision, you need context. The `get_user_profile` tool provides identity data for auditing purposes in Vertex AI. Similarly, `get_task_details` gives the full scope of any single task. These retrieval tools ensure that every action taken by your agent is traceable and tied back to specific user or project records.

Setup guide

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

You instruct the agent to call `list_plans`. This tool returns a complete manifest of every plan, which your Gemini model can then ingest and process against other BigQuery data.

Absolutely. By calling `create_task` with a title and optional start time, you let your agent build new entries directly into Structured for immediate tracking.

The server exposes the current user profile through `get_user_profile`. Your agent can use this tool to verify identity and scope before performing write operations on Structured.

Use `list_tasks` first to see everything. Then, if you need to make a change, use `update_task`. This two-step process is clean and reliable for maintaining data integrity.

This MCP Server touches user profile data. When planning, ensure that the agent only requests `get_user_profile` if it has been explicitly vetted for handling personally identifiable information.

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