How to Use the LiveKit MCP in LlamaIndex

Q: How do I index LiveKit participant lists into LlamaIndex?

You call listparticipants through the indexer to ingest the active user directory. LlamaIndex then converts this data into document nodes for vector storage.

Q: Can I query active LiveKit rooms using LlamaIndex RAG?

Absolutely, because listrooms feeds live data directly into your query engine. The agent retrieves the current state before generating any response.

Q: How do I search LiveKit phone numbers with LlamaIndex?

You run listphonenumbers to pull your inventory, index the results, and let your LlamaIndex agent match numbers to regions.

Q: Can this MCP Server fetch individual track details?

Yes, the server provides getparticipant which returns detailed track subscriptions. Your agent uses this to map out which audio and video feeds are active.

Q: Where are my LiveKit SIP trunk configurations stored?

All SIP details, including credentials passed via createsipinboundtrunk, remain inside your secure Vinkius MCP sandbox. No configuration data is ever cached or exposed to third parties.

Index LiveKit room data and participant tracks into LlamaIndex to run semantic search over your communication history.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiveKit MCP to LlamaIndex

Create your Vinkius account to connect LiveKit 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 LiveKit with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index LiveKit Metadata into Vector Stores

LlamaIndex turns your live communication data into a searchable knowledge base. Your agent uses this MCP Server to run `list_rooms` and `get_participant` to retrieve active session data, then indexes those details directly into your vector database. This prevents you from losing track of who was in which meeting. You can query your past room configurations using natural language instead of writing complex database queries.

Ground RAG Applications in Live Room Data

Hallucinations ruin automated session management. By using this MCP Server, your LlamaIndex agent fetches real-time states using `list_participants` to ground its answers in actual, current room data. Your agent always knows who is currently connected before making decisions. If you ask who is speaking, the agent checks the live tracks instead of guessing based on outdated logs.

Query LiveKit Egress Records with LlamaIndex MCP Server

Tracking down past recordings becomes simple when your indexer knows your layout history. Use `list_egress` to pull active or past recording jobs, then let LlamaIndex parse the configurations for semantic retrieval. You can easily find which layout was used for a specific session. The agent cross-references your egress logs with room metadata to give you a complete picture of your recorded media.

Setup guide

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

You call `list_participants` through the indexer to ingest the active user directory. LlamaIndex then converts this data into document nodes for vector storage.

Absolutely, because `list_rooms` feeds live data directly into your query engine. The agent retrieves the current state before generating any response.

You run `list_phone_numbers` to pull your inventory, index the results, and let your LlamaIndex agent match numbers to regions.

Yes, the server provides `get_participant` which returns detailed track subscriptions. Your agent uses this to map out which audio and video feeds are active.

All SIP details, including credentials passed via `create_sip_inbound_trunk`, remain inside your secure Vinkius MCP sandbox. No configuration data is ever cached or exposed to third parties.

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