How to Use the Liveblocks MCP in OpenAI Agents SDK

Q: How do I install the Liveblocks MCP Server for my OpenAI Agents SDK project?

Run pip install openai-agents in your terminal. Instantiate MCPServerStreamableHttp using your Vinkius HTTP endpoint, then pass that server object into your agent's constructor inside an async context manager.

Q: Can my OpenAI Agents SDK system use Liveblocks to handle real-time events?

Yes. The agent uses broadcastevent to inject custom JSON payloads directly into active rooms. This triggers immediate updates on the frontend without waiting for a database write.

Q: How does the Liveblocks MCP Server handle user authorization in OpenAI Agents SDK?

The agent calls authorizeuser or identifyuser to generate secure tokens. These tokens let your frontend clients safely connect to Liveblocks rooms with specific read or write permissions.

Q: Does this MCP integration support multi-agent handoffs?

Yes. One specialized agent can run listrooms to find stale workspaces, then hand off the room ID to a cleanup agent that runs deleteroom.

Let your OpenAI Agents SDK production deployment manage multi-user collaboration spaces and resolve comment threads autonomously.

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 OpenAI Agents SDK

Create your Vinkius account to connect Liveblocks 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Room Setups via OpenAI Agents SDK

The `create_room` tool lets your agent provision isolated collaboration spaces on demand. Your code runs within the `openai-agents` runtime, allowing your agent to dynamically assign user permissions using `authorize_user` right after a room goes live via the MCP Server. If a user requests access to a workspace, the agent checks your database, fires `get_room` to confirm the space exists, and generates the access token. This setup bypasses manual backend routing, keeping your workspace configuration safe under OpenAI's built-in guardrails.

Inspect and Modify Liveblocks State Trees

The `get_storage` tool pulls raw JSON state trees directly into your agent's context window. Your agent can run `patch_storage` to modify specific collaborative properties without wiping out the entire state or conflicting with active client sessions. For complex Yjs applications, the agent uses `get_ydoc` to inspect binary document states or pushes updates back using `update_ydoc`. Enabling `cacheToolsList=True` in your server parameters ensures these lookups execute with minimal latency during multi-agent handoffs.

Resolve User Issues inside Threads

The `list_threads` tool retrieves all active discussion threads within a specific room. Your agent reads through the comments using `get_thread`, analyzes the user's issue, and writes a response directly to the thread using `create_thread`. Once the agent verifies the issue is fixed, it calls `resolve_thread` to close the loop. This entire interaction is tracked in your OpenAI dashboard, so you can audit how the agent handles user feedback.

Setup guide

Set up Liveblocks 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 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Liveblocks 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 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 Agent",
            instructions="You have access to Liveblocks 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 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 OpenAI Agents SDK

Run `pip install openai-agents` in your terminal. Instantiate `MCPServerStreamableHttp` using your Vinkius HTTP endpoint, then pass that server object into your agent's constructor inside an async context manager.

Yes. The agent uses `broadcast_event` to inject custom JSON payloads directly into active rooms. This triggers immediate updates on the frontend without waiting for a database write.

The agent calls `authorize_user` or `identify_user` to generate secure tokens. These tokens let your frontend clients safely connect to Liveblocks rooms with specific read or write permissions.

Yes. One specialized agent can run `list_rooms` to find stale workspaces, then hand off the room ID to a cleanup agent that runs `delete_room`.

Your JSON storage patches, Yjs documents, and comment threads are transmitted over encrypted HTTPS. Vinkius runs the server in an ephemeral sandbox, ensuring user IDs and room metadata are never written to persistent disk storage.

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