How to Use the Liveblocks (Collaborative) MCP in Google ADK

Q: How do I configure Liveblocks (Collaborative) within the Google ADK?

Install google-adk and define an McpToolset pointing to your HTTP MCP Server URL. Pass this toolset to your LlmAgent instance. You can use the toolnames filter if you want to restrict the agent to specific tools like getstorage.

Q: Can Gemini write directly to Liveblocks collaborative documents?

Yes. Gemini can use patchstorage to apply precise updates to the room's shared state. This allows the model to inject structured text or data tables directly into a live document while users are editing.

Q: How do I track active users in Google ADK agent workflows?

Your agent can run listactiveusers to see who is currently online in a room. This is useful for triggering automated notifications or agent actions when specific team members join the session.

Q: Can I use Liveblocks (Collaborative) to manage user comments in Google ADK?

Yes. The agent can fetch discussion history using listthreads and participate by calling createthread to post new comments directly into the collaborative UI.

Connect Gemini's 1M-token context to live collaborative spaces 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 (Collaborative) MCP to Google ADK

Create your Vinkius account to connect Liveblocks (Collaborative) 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 (Collaborative) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze massive collaborative histories with this MCP Server.

This MCP Server allows your Gemini agent to pull complete Liveblocks room states using `get_room` and feed them directly into Vertex AI. Because Gemini supports massive context windows, you can load entire Liveblocks document histories without losing detail. The Gemini agent can use `list_versions` to fetch the Yjs version history of a Liveblocks document and compare it against enterprise datasets stored in BigQuery.

Coordinate enterprise workspaces at scale.

The `list_rooms` and `update_room` tools give your Google ADK agent the ability to organize complex Liveblocks workspace hierarchies. You can filter Liveblocks rooms by metadata tags that match your Google Cloud project structures managed by the Google ADK agent. When a project milestone is reached, the Google ADK agent can call `delete_room` to clean up temporary Liveblocks environments.

Sync live data pipelines with real-time storage.

The `get_storage` and `patch_storage` tools let your Google ADK agent bridge the gap between your Google Cloud databases and live Liveblocks documents. Your Google ADK agent can read structured data from BigQuery and write it directly into a Liveblocks room's storage tree. If users make edits, the Google ADK agent reads the updated Liveblocks state and syncs it back to your data warehouse.

Setup guide

Set up Liveblocks (Collaborative) 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 (Collaborative) 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 (Collaborative)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Liveblocks (Collaborative) 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 (Collaborative) 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 (Collaborative) MCP in Google ADK

Install `google-adk` and define an `McpToolset` pointing to your HTTP MCP Server URL. Pass this toolset to your `LlmAgent` instance. You can use the `tool_names` filter if you want to restrict the agent to specific tools like `get_storage`.

Yes. Gemini can use `patch_storage` to apply precise updates to the room's shared state. This allows the model to inject structured text or data tables directly into a live document while users are editing.

Your agent can run `list_active_users` to see who is currently online in a room. This is useful for triggering automated notifications or agent actions when specific team members join the session.

Yes. The agent can fetch discussion history using `list_threads` and participate by calling `create_thread` to post new comments directly into the collaborative UI.

This server handles ephemeral user presence metrics, room permissions, and collaborative JSON storage trees. The Vinkius V8 Isolate sandbox ensures that no third party can intercept these payloads, keeping your enterprise data fully isolated.

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