How to Use the Vidyard MCP in LlamaIndex

Q: How do I query past Vidyard player configurations using LlamaIndex?

You run the listvideoplayers tool and feed those results into your index. The agent can then answer questions about previously configured players, drawing from the stored data rather than just live API calls.

Q: What if I need to search video source details for Vidyard with LlamaIndex?

You use getvideosourcefiles and index the resulting direct stream URLs. This allows your RAG application to answer highly specific questions about available video qualities based on the indexed data.

Q: Can I track Vidyard asset changes with LlamaIndex?

Yes. By indexing output from listvideos and combining it with getvideodetails, you build a timeline of assets. Your agent can query the index to see what metadata was available for an asset at a specific point in time.

Q: Does LlamaIndex handle Vidyard player state management?

It indexes the output of getplayerdetails. This means that when you run the tool, the resulting details are stored in your vector store, making them retrievable for future queries.

Index Vidyard player and video data into knowledge graphs 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 Vidyard MCP to LlamaIndex

Create your Vinkius account to connect Vidyard 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 Vidyard with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a searchable index of all players.

To build your RAG application, you first call `list_video_players`. This list of facade names is then indexed into the vector store. You can query past configurations to find which players exist without needing to run live API calls. Later on, if you need specific info, calling `get_player_details` retrieves fresh data that updates your knowledge base.

Index video source files for deep search.

When a user needs to know what formats are available, you use `get_video_source_files`. The resulting direct stream URLs (480p, 720p, etc.) become searchable knowledge. You index these specific technical metrics. This lets the agent answer questions like 'What video quality is available for this asset?' based on indexed API results.

Retrieve and index all stored videos.

You start by calling `list_videos` to get names of every stored asset. This list forms the basis of your knowledge graph, letting you search across the entire Vidyard library. If you find a relevant video ID, you can then use `get_video_details` to enrich that index entry with technical metadata for better semantic retrieval.

Setup guide

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

You run the `list_video_players` tool and feed those results into your index. The agent can then answer questions about previously configured players, drawing from the stored data rather than just live API calls.

You use `get_video_source_files` and index the resulting direct stream URLs. This allows your RAG application to answer highly specific questions about available video qualities based on the indexed data.

Yes. By indexing output from `list_videos` and combining it with `get_video_details`, you build a timeline of assets. Your agent can query the index to see what metadata was available for an asset at a specific point in time.

It indexes the output of `get_player_details`. This means that when you run the tool, the resulting details are stored in your vector store, making them retrievable for future queries.

The server touches video asset IDs and player container metadata. When building your index, you control which specific fields are extracted and stored, ensuring the knowledge base only contains necessary identifiers.

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