How to Use the Liveblocks MCP in Google ADK

Q: How do I configure the Liveblocks MCP Server within Google ADK?

Install the package via pip install google-adk. Initialize McpToolset with your Vinkius HTTP URL, then pass it to your LlmAgent tools array to expose the collaboration tools.

Q: How does my Google ADK agent use Liveblocks to collaborate with users?

Gemini calls createthread to start conversations in the UI and uses listthreads to read user feedback. This lets the model participate directly in the team's existing chat interface.

Let Gemini analyze BigQuery data and modify collaborative workspaces using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Liveblocks MCP to Google ADK

Create your Vinkius account to connect Liveblocks 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 Liveblocks with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Workspaces to Gemini via Google ADK

The `get_storage` tool retrieves the entire collaborative state tree of a room and dumps it into Gemini's 1M+ token window. Using the Google ADK, your agent processes complex, multi-user document structures alongside historical data pulled from BigQuery. When Gemini identifies a discrepancy, it executes `patch_storage` to update the shared workspace state instantly. This tight loop allows enterprise agents to fix document errors without human intervention.

Track Active Users and Dispatch Custom Events

The `list_active_users` tool exposes who is currently working inside a specific room. Your agent uses this list to coordinate real-time workflows, ensuring it only sends critical updates when human collaborators are online. To ping those active users, the agent runs `broadcast_event` to push immediate notifications to the client browser. This keeps human teams and your Gemini-powered agent perfectly in sync.

Provision Rooms via the Liveblocks MCP Server

The `create_room` tool allows your agent to spin up new collaborative environments based on enterprise events. Your Google ADK agent monitors Vertex AI pipelines and automatically configures a new room when a training job completes. The agent then calls `update_room` to set metadata or restrict access, and uses `delete_room` to clean up temporary spaces. This automation removes the manual overhead of managing thousands of distinct project rooms.

Setup guide

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

Install the package via `pip install google-adk`. Initialize `McpToolset` with your Vinkius HTTP URL, then pass it to your `LlmAgent` tools array to expose the collaboration tools.

Yes. You can restrict the toolset by passing a list of allowed tool names to the `tool_names` parameter when initializing your `McpToolset`.

Gemini calls `create_thread` to start conversations in the UI and uses `list_threads` to read user feedback. This lets the model participate directly in the team's existing chat interface.

Yes, the Google ADK supports both transport layers. For managed cloud deployments, use the streamable HTTP transport pointing to your secure MCP endpoint.

Room metadata, user IDs, and Yjs binary updates are routed directly to Liveblocks. The MCP Server sandbox operates on a zero-trust model, meaning no collaborative state is stored on Vinkius servers.

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