How to Use the Liveblocks (Collaborative) MCP in LlamaIndex

Q: Can I index Liveblocks (Collaborative) thread comments into a LlamaIndex vector store?

Yes. Your agent uses listthreads to fetch all comments and discussion metadata from a room. LlamaIndex then parses these text blocks into document nodes for semantic search.

Q: How does LlamaIndex query live document states in Liveblocks (Collaborative) via this MCP Server?

The agent calls getydoc or getstorage to pull the latest JSON snapshot of the collaborative state. It indexes this data on the fly, making it immediately available for retrieval-augmented generation.

Q: Does LlamaIndex support updating Liveblocks (Collaborative) storage schemas?

Yes, the MCP server lets your agent use initializestorage or patchstorage to modify the shared state. This allows you to programmatically update room storage based on insights retrieved from your knowledge base.

Q: How do I filter rooms during indexing?

You pass filter parameters to the listrooms tool. The agent retrieves only the rooms that match your criteria, saving API quota and keeping your vector index focused on relevant workspaces.

Index live collaborative session data into your LlamaIndex vector stores for context-rich RAG applications.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index collaborative document history into LlamaIndex

The `get_ydoc` tool retrieves the raw JSON representation of any active collaborative document. Your LlamaIndex agent pulls this document state and passes it directly to vector store indexers. This converts your live collaborative canvas into searchable knowledge, preventing your LlamaIndex agent from hallucinating about current project states. To track changes over time, the LlamaIndex agent calls `list_versions` to fetch the history of the document. It parses these snapshots, allowing users to query past states of the workspace using natural language. You get a search system grounded in actual, historical document data retrieved via LlamaIndex.

Query active room metadata and user presence

The `list_rooms` tool searches and paginates through all active collaborative workspaces based on your filters. Your LlamaIndex agent feeds this list into a query engine so you can ask which rooms are currently active or who owns them. It parses the metadata returned by `get_room` to build a semantic map of your organization's workspaces in LlamaIndex. Tracking active participants is handled by `list_active_users`, which returns a list of users currently connected to a room. The LlamaIndex agent indexes this presence data to help you find who is working on what in real time. This makes your LlamaIndex knowledge base reflect live human activity, not just static files.

Search and update collaborative threads via MCP Server

The `list_threads` tool retrieves all comments and discussions happening inside a collaborative room. LlamaIndex indexes these conversations, making team decisions and feedback searchable for your agent. When a user asks why a design choice was made, the LlamaIndex agent searches past threads to find the exact comment. If the LlamaIndex agent needs to add to the conversation, it uses `create_thread` to post a new comment or `resolve_thread` to close out a resolved issue. It can also initialize storage schemas using `initialize_storage` before users start editing. This keeps your LlamaIndex communication loops and document structures organized.

Setup guide

Set up Liveblocks (Collaborative) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Liveblocks (Collaborative) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Liveblocks (Collaborative) tools.",
)
response = await agent.run("List recent Liveblocks (Collaborative) data")

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 LlamaIndex

Yes. Your agent uses `list_threads` to fetch all comments and discussion metadata from a room. LlamaIndex then parses these text blocks into document nodes for semantic search.

The agent calls `get_ydoc` or `get_storage` to pull the latest JSON snapshot of the collaborative state. It indexes this data on the fly, making it immediately available for retrieval-augmented generation.

Yes, the MCP server lets your agent use `initialize_storage` or `patch_storage` to modify the shared state. This allows you to programmatically update room storage based on insights retrieved from your knowledge base.

You pass filter parameters to the `list_rooms` tool. The agent retrieves only the rooms that match your criteria, saving API quota and keeping your vector index focused on relevant workspaces.

Your Yjs binary updates and thread comments are processed locally. This MCP server handles operations in secure, ephemeral sandboxes, sending data directly to your specified LlamaIndex vector store without caching.

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