How to Use the Liveblocks MCP in LlamaIndex

Q: Can LlamaIndex query historical threads from Liveblocks?

Yes. LlamaIndex pulls thread data using listthreads and indexes it into a vector store. This allows semantic queries over past user discussions inside specific rooms.

Q: How does LlamaIndex handle Yjs documents from Liveblocks?

The framework uses getydoc to retrieve the JSON representation of the Yjs document. The MCP server fetches this data, then LlamaIndex chunks and indexes this JSON structure so your agent can search collaborative state.

Q: Can I filter LlamaIndex queries by Liveblocks room metadata?

Yes, you can use listrooms to filter rooms by metadata before indexing. This ensures your LlamaIndex search queries are constrained to the correct collaborative context via the Liveblocks MCP server.

Q: How often should I update the LlamaIndex vector store with live room data?

You can trigger an indexing run whenever patchstorage is called, or set up a polling interval. This keeps your vector store synchronized with the live collaborative state.

Index live collaborative data from Liveblocks directly into LlamaIndex vector stores for grounded, real-time RAG.

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 LlamaIndex

Create your Vinkius account to connect Liveblocks 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 with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Liveblocks MCP Server Collaborative State

Stop letting your RAG applications guess what is happening on the user's screen. By fetching live document trees with `get_storage` and `get_ydoc`, LlamaIndex indexes the actual state of your collaborative whiteboard or text editor. The framework parses this structured data, turning live room updates into searchable vector nodes via this MCP tool. Your agent queries this index to answer user questions based on the exact, current state of their collaborative workspace.

Semantic Search Over Live Conversations

Pull active user discussions into your knowledge base by indexing threads. The agent calls `list_threads` and `get_thread` to ingest user comments, converting raw text into semantic embeddings. This lets your LlamaIndex agent retrieve past resolutions when a user asks about a previous decision. It can even use `create_thread` to suggest answers directly inside the room when a matching topic is queried.

Dynamic Context Retrieval for Active Rooms

Ground your agent's responses in current room activity. By querying `list_active_users` and `get_room`, the LlamaIndex agent determines who is active and what metadata is set before retrieving relevant documents. This ensures the retrieved context matches the specific room profile. The agent can then use `broadcast_event` to send highly relevant, retrieved facts directly to the active users in the room.

Setup guide

Set up Liveblocks 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 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 tools.",
)
response = await agent.run("List recent Liveblocks 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 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 LlamaIndex

Yes. LlamaIndex pulls thread data using `list_threads` and indexes it into a vector store. This allows semantic queries over past user discussions inside specific rooms.

The framework uses `get_ydoc` to retrieve the JSON representation of the Yjs document. The MCP server fetches this data, then LlamaIndex chunks and indexes this JSON structure so your agent can search collaborative state.

Yes, you can use `list_rooms` to filter rooms by metadata before indexing. This ensures your LlamaIndex search queries are constrained to the correct collaborative context via the Liveblocks MCP server.

You can trigger an indexing run whenever `patch_storage` is called, or set up a polling interval. This keeps your vector store synchronized with the live collaborative state.

All room metadata and thread content retrieved by the MCP server are processed in-memory within Vinkius's secure sandbox. No collaborative data is cached or stored permanently outside of your own LlamaIndex vector store and Liveblocks database.

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