How to Use the api.video MCP in LlamaIndex

Q: How can LlamaIndex query my api.video captions and chapters?

You'll use the listvideocaptions and listvideochapters tools to pull the text data. Then, you add that text to your LlamaIndex data loaders to be indexed into your vector store for semantic search.

Q: Can I build a LlamaIndex agent that finds api.video videos based on their performance?

Yes. You can index analytics data from getvideoanalytics alongside metadata. This lets your agent answer queries like "Show me the top 5 performing videos from last month."

Q: What's the setup for making api.video tools available to a LlamaIndex agent?

After installing the MCP tools package, you create a BasicMCPClient with your Vinkius URL. Then, you wrap it in an McpToolSpec and call .totoollistasync() to get the tools for your agent.

Turn your api.video library into a searchable knowledge base for your LlamaIndex 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 api.video MCP to LlamaIndex

Create your Vinkius account to connect api.video 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 api.video with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index your entire video catalog

Use the `list_videos` and `get_video_details` tools to ingest all your video metadata. LlamaIndex doesn't just fetch the data once; it indexes it into a vector store of your choice. Now your agent has a persistent, searchable knowledge base of your video library. You can ask it questions like "Which videos are about our Q3 launch?" and get answers grounded in your actual content.

Combine semantic search with live data

This is where it gets interesting. Your agent can query the index for videos on a certain topic, then use the `get_video_analytics` tool to fetch live performance metrics for just those videos. It's a two-step process that combines the broad knowledge of your indexed library with the precision of a real-time API call. This happens inside a single query, giving you answers that are both context-aware and up-to-date.

Build a RAG system on your MCP Server

You can build a powerful RAG application on top of your video content. Use the provided tools to index not just titles, but also chapters from `list_video_chapters` and captions from `list_video_captions`. Your LlamaIndex agent can now answer complex questions by synthesizing information from all these sources. It can find specific moments in videos based on the spoken words in your captions, all through a natural language query.

Setup guide

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

You'll use the `list_video_captions` and `list_video_chapters` tools to pull the text data. Then, you add that text to your LlamaIndex data loaders to be indexed into your vector store for semantic search.

Yes. You can index analytics data from `get_video_analytics` alongside metadata. This lets your agent answer queries like "Show me the top 5 performing videos from last month."

After installing the MCP tools package, you create a `BasicMCPClient` with your Vinkius URL. Then, you wrap it in an `McpToolSpec` and call `.to_tool_list_async()` to get the tools for your agent.

No. LlamaIndex and this MCP server only work with text-based data: video metadata, captions, chapters, and analytics numbers. Your video files themselves are never downloaded or indexed.

Only the video metadata, captions, chapter lists, and analytics data you explicitly index are processed. The server itself is ephemeral, and Vinkius isolates each request, so your indexed content isn't exposed to other users.

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