How to Use the Liveblocks (Collaborative) MCP in LangChain

Q: How does LangChain handle Liveblocks (Collaborative) token authorization?

Your agent calls authorizeuser or identifyuser during a chain run to fetch a temporary token. This token gets passed to the client-side Liveblocks runner to securely authenticate the active user session.

Q: Can a LangChain agent edit a shared document using this MCP Server?

Yes. The agent uses updateydoc to send binary updates or patchstorage to modify specific keys in the shared JSON storage tree. LangChain traces these tool calls so you can monitor the exact payload sent to the room.

Q: Does this MCP Server support real-time event broadcasting?

Yes, this MCP server exposes the broadcastevent tool. Your agent uses this to send custom JSON events to all active users in a room instantly, bypassing persistent storage for transient UI updates.

Manage multi-user collaborative rooms and live document states directly within your LangChain reasoning chains.

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 LangChain

Create your Vinkius account to connect Liveblocks (Collaborative) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage collaborative rooms inside LangChain chains

The `create_room` tool lets your agent provision new collaborative spaces instantly based on user prompts. After creating a room, the agent immediately uses `authorize_user` to grant specific read or write permissions to developers or clients. This sequence runs as a single, observable chain, allowing you to trace exactly how and when access tokens are issued. Your agent handles room lifecycles by running `update_room` to modify metadata on the fly. If a project wraps up, the agent invokes `delete_room` to clean up the workspace. You see every step of these state changes inside your LangSmith dashboard with exact latency metrics.

Sync real-time document states via MCP Server tools

The `update_ydoc` tool syncs binary Yjs document state changes across active collaborative sessions. When your LangChain agent needs to read the current state, it calls `get_ydoc` to pull down the JSON representation of the shared document. This setup lets your LangChain chain act as a virtual collaborator that reads and writes directly to the shared canvas. For structured data, the agent applies JSON Patch operations directly using `patch_storage`. It reads the current tree with `get_storage` to ensure it has the correct schema before sending updates. These tools allow your LangChain agent to modify shared UI states without overwriting changes made by human users.

Moderate active threads and user presence

The `list_active_users` tool monitors who is currently working inside a specific workspace. Your LangChain agent uses this data alongside `set_presence` to show its own online status or coordinate tasks based on user availability. If a user needs help, your LangChain chain calls `create_thread` to start a discussion thread with an initial comment. Resolving issues becomes programmatic when the LangChain agent executes `resolve_thread` after addressing a user's question. It lists outstanding items with `list_threads` to keep track of what still needs attention. This turns your LangChain agent into an active, helpful participant in the team's shared workspace.

Setup guide

Set up Liveblocks (Collaborative) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Liveblocks (Collaborative) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "liveblocks-collaborative-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Liveblocks (Collaborative) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your agent calls `authorize_user` or `identify_user` during a chain run to fetch a temporary token. This token gets passed to the client-side Liveblocks runner to securely authenticate the active user session.

Yes. The agent uses `update_ydoc` to send binary updates or `patch_storage` to modify specific keys in the shared JSON storage tree. LangChain traces these tool calls so you can monitor the exact payload sent to the room.

You use LangSmith to trace every single tool call, including inputs and outputs for operations like `get_storage`. This gives you clear visibility into latency and token usage for your collaborative workflows.

Yes, this MCP server exposes the `broadcast_event` tool. Your agent uses this to send custom JSON events to all active users in a room instantly, bypassing persistent storage for transient UI updates.

This server only transmits your Yjs binary states, room metadata, and thread comments through ephemeral memory isolates. No collaborative room data is stored on Vinkius servers, keeping your active editing sessions private.

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