How to Use the Liveblocks (Collaborative) MCP in OpenAI Agents SDK

Q: How do I connect Liveblocks (Collaborative) to the OpenAI Agents SDK?

Install openai-agents and initialize the MCP Server using the HTTP streamable transport pointing to your Vinkius endpoint. Pass this instance in the mcpservers list when instantiating your Agent. Make sure to set cacheToolsList=True to prevent overhead during initialization.

Q: Can my agent handle Yjs document updates safely?

Yes. Your agent can call getydoc to fetch the current document state and updateydoc to push binary updates. The built-in guardrails in the SDK let you inspect these binary payloads before they execute.

Q: How do I restrict room management permissions in Liveblocks (Collaborative) with OpenAI Agents SDK?

Use authorizeuser to generate scoped tokens. Your agent can dynamically request permissions for specific rooms, preventing it from executing deleteroom or modifying metadata unless explicitly allowed.

Q: Does this integration support agent handoffs for thread resolution?

Yes. A triage agent can monitor rooms using listthreads and hand off the context to a resolver agent that executes resolvethread once the underlying issue is fixed.

Build self-correcting collaborative workflows with the OpenAI Agents SDK and Liveblocks.

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 OpenAI Agents SDK

Create your Vinkius account to connect Liveblocks (Collaborative) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build secure multi-agent rooms using this MCP Server.

This MCP Server lets your OpenAI agent manage collaborative spaces by invoking `create_room` and `update_room` directly from your Python runtime. When building production multi-agent systems, you need strict boundaries on who can edit what in your collaborative documents. The OpenAI agent can programmatically issue scoped tokens using `authorize_user` to ensure users only access their designated Liveblocks rooms.

Track live presence and sync state in real time.

The `list_active_users` and `set_presence` tools give your OpenAI agents direct visibility into who is currently working in a Liveblocks room. Instead of polling database tables, your OpenAI agent queries the live socket state to see active collaborative sessions. When users make changes, the OpenAI agent can run `patch_storage` to apply atomic JSON updates directly to the shared Liveblocks document state.

Manage threads and broadcast live events.

The `create_thread` and `resolve_thread` tools allow your OpenAI agent to participate in human-in-the-loop Liveblocks discussions. When the OpenAI agent detects an error in the document, it leaves a comment in the Liveblocks thread to alert the team. For instant updates, the OpenAI agent uses `broadcast_event` to send transient JSON payloads directly to active collaborative clients.

Setup guide

Set up Liveblocks (Collaborative) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Liveblocks (Collaborative) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Liveblocks (Collaborative) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Liveblocks (Collaborative) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Liveblocks (Collaborative) Agent",
            instructions="You have access to Liveblocks (Collaborative) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` and initialize the MCP Server using the HTTP streamable transport pointing to your Vinkius endpoint. Pass this instance in the `mcp_servers` list when instantiating your Agent. Make sure to set `cacheToolsList=True` to prevent overhead during initialization.

Yes. Your agent can call `get_ydoc` to fetch the current document state and `update_ydoc` to push binary updates. The built-in guardrails in the SDK let you inspect these binary payloads before they execute.

Use `authorize_user` to generate scoped tokens. Your agent can dynamically request permissions for specific rooms, preventing it from executing `delete_room` or modifying metadata unless explicitly allowed.

Yes. A triage agent can monitor rooms using `list_threads` and hand off the context to a resolver agent that executes `resolve_thread` once the underlying issue is fixed.

This server processes live collaborative metadata, room storage trees, and Yjs binary documents. All operations run inside Vinkius's zero-trust V8 sandbox, meaning your raw room data is never stored on intermediate servers and is transmitted directly to your Liveblocks endpoint.

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