How to Use the 100ms MCP in LlamaIndex

Q: How do I add 100ms tools to a LlamaIndex agent?

You install llama-index-tools-mcp and instantiate the BasicMCPClient to connect to the 100ms MCP Server. Wrap the client in McpToolSpec and pass the converted tool list to your FunctionAgent constructor.

Q: Can LlamaIndex index 100ms video recording paths?

Yes, your agent can call listrecordings using the MCP tool to retrieve paths and index them as document nodes. This makes your video assets discoverable via standard semantic search queries.

Q: How do I query 100ms room details using LlamaIndex?

The agent calls getroom to fetch the configuration JSON and parses it into a document. This document is loaded into your index, making room settings queryable using natural language.

Q: Can LlamaIndex filter 100ms sessions before indexing them?

You can configure the agent to call listsessions with specific filters like room ID or status. The agent only indexes the sessions that meet your criteria, saving vector database storage.

Index your live video metadata directly into LlamaIndex to query past sessions and participant histories.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 100ms MCP to LlamaIndex

Create your Vinkius account to connect 100ms 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 100ms with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index 100ms session metadata into your RAG pipeline

Your agent runs `list_sessions` to turn live call details into searchable vector embeddings. It pulls raw attendance logs and metadata, then indexes them directly into your vector store. This eliminates blind spots in your company knowledge base. Instead of guessing who attended a meeting last month, you query your LlamaIndex agent to get answers grounded in actual session logs.

Search room configurations using natural language queries

Your agent uses `list_rooms` to pull all active room definitions and index their properties. When you ask which rooms have recording enabled, the agent queries the index instead of making repeated API calls. You avoid writing complex filtering logic for your video infrastructure. The agent resolves your intent against the indexed room configurations and returns the exact matching room IDs instantly.

Track participant patterns with LlamaIndex MCP Server tools

Your agent indexes active participants by calling `list_peers` across your active sessions. It stores this live state in your document index, allowing you to run semantic queries on current platform usage. You get an instant, conversational view of your active video network. The agent matches user queries against the indexed participant data, identifying who is online without manual dashboard checks.

Setup guide

Set up 100ms 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 100ms 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 100ms tools.",
)
response = await agent.run("List recent 100ms 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 100ms. 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 100ms 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 100ms MCP in LlamaIndex

You install `llama-index-tools-mcp` and instantiate the BasicMCPClient to connect to the 100ms MCP Server. Wrap the client in `McpToolSpec` and pass the converted tool list to your `FunctionAgent` constructor.

Yes, your agent can call `list_recordings` using the MCP tool to retrieve paths and index them as document nodes. This makes your video assets discoverable via standard semantic search queries.

The agent calls `get_room` to fetch the configuration JSON and parses it into a document. This document is loaded into your index, making room settings queryable using natural language.

You can configure the agent to call `list_sessions` with specific filters like room ID or status. The agent only indexes the sessions that meet your criteria, saving vector database storage.

Your session logs and room metadata are processed ephemerally using an MCP sandbox. The server runs in a sandboxed environment, ensuring that participant names and meeting IDs are never logged or stored.

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