How to Use the YouTube MCP in LlamaIndex

Q: How does LlamaIndex manage YouTube video metadata?

LlamaIndex takes the raw JSON output from searchvideos and converts it into searchable knowledge chunks. You query these indices, getting answers grounded in the actual video descriptions and titles.

Q: Can I query past YouTube stats using LlamaIndex?

Yes. Every time you run getchannel, LlamaIndex indexes those statistics. You can then query your knowledge base to compare current performance against historical records automatically.

Q: How do I use the MCP Server for YouTube analysis in LlamaIndex?

You connect the tools via BasicMCPClient and pass them into a FunctionAgent. The agent then treats every tool call—like getvideo or listcomments—as data that must be indexed before answering your query.

Index YouTube Data into Knowledge Bases with LlamaIndex

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect YouTube MCP to LlamaIndex

Create your Vinkius account to connect YouTube 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 YouTube with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Search Across YouTube Videos

Don't just call the tool—index the results. When you run `search_videos`, LlamaIndex takes the returned video metadata and turns it into a searchable vector store. You can then query past searches to find videos related by concept, not just keyword. This means your RAG application grounds answers in actual YouTube data, letting you ask questions like 'What were the top topics covered last month?'

Building Knowledge Bases from MCP Server Data

Use `get_channel` to pull a channel’s entire performance profile. LlamaIndex indexes this data, allowing you to query its history later. You can ask it to compare the current stats against last quarter's indexed metrics. It treats live API calls as permanent knowledge chunks, making every piece of YouTube data instantly retrievable for semantic search.

Auditing Comments and Descriptions via LlamaIndex

When you use `get_video` or `list_comments`, the returned text—the description or comment threads—gets indexed. This lets your agent run sophisticated queries against the *text* content, surfacing specific opinions or themes from hundreds of comments. This is much better than just listing comments; it’s summarizing the underlying sentiment found in the data.

Setup guide

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

LlamaIndex takes the raw JSON output from `search_videos` and converts it into searchable knowledge chunks. You query these indices, getting answers grounded in the actual video descriptions and titles.

Yes. Every time you run `get_channel`, LlamaIndex indexes those statistics. You can then query your knowledge base to compare current performance against historical records automatically.

You connect the tools via `BasicMCPClient` and pass them into a FunctionAgent. The agent then treats every tool call—like `get_video` or `list_comments`—as data that must be indexed before answering your query.

Definitely. Calling a tool gives you a snapshot; indexing the results turns that snapshot into a persistent, searchable knowledge asset. You gain context and history.

The server handles public video descriptions, channel statistics, and comment threads. The specific data types you index are text strings and numerical metrics.

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