How to Use the Livepeer (Decentralized Video) MCP in LlamaIndex

Q: How does LlamaIndex index live data from the Livepeer (Decentralized Video) MCP Server?

LlamaIndex calls tools like listassets or getviewershipmetrics and converts the JSON outputs into Document objects. These documents are then split, embedded, and stored in your vector database, making your video data searchable in real time.

Q: Can I use Livepeer (Decentralized Video) with LlamaIndex to query transcoding usage metrics?

Yes, you can query getusagemetrics to retrieve data on total minutes transcoded and delivered. Your LlamaIndex agent can then index this financial data to help you track costs and predict future infrastructure spend.

Q: How does a LlamaIndex agent resolve playback issues using Livepeer (Decentralized Video) tools?

The agent can query getplaybackinfo to retrieve the active playback URLs and metadata. By comparing this live data with indexed configuration files, the agent can pinpoint misconfigured streams and recommend the exact fix.

Q: Can I filter which Livepeer tools are exposed to my LlamaIndex agent using MCP?

Yes, you can use LlamaIndex's allowedtools filter when loading the MCP server. This lets you restrict your agent to read-only tools like getasset and liststreams while blocking destructive tools like deletestream.

Ground your LlamaIndex RAG applications in real-time video analytics and stream configurations using our Livepeer MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Livepeer (Decentralized Video) MCP to LlamaIndex

Create your Vinkius account to connect Livepeer (Decentralized 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 Livepeer (Decentralized Video) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Livepeer video metadata directly into LlamaIndex

Turn your video assets into searchable knowledge. Your agent can call `list_assets` and `get_asset` to fetch metadata, descriptions, and processing states, then index that data directly into your local vector store. This lets you build search tools that answer complex questions about your media library. Instead of guessing, your agent queries the indexed metadata to find specific files, check their status, or retrieve playback URLs via `get_playback_info`.

Query historical viewership and performance metrics

Build RAG pipelines that understand your audience trends. The agent pulls detailed analytics using `get_viewership_metrics` and `get_usage_metrics`, storing the historical data as documents within your index. Users can ask questions about viewer distribution or transcoding costs in plain English. The agent retrieves the relevant metrics from the index, giving you grounded answers based on actual usage data.

Manage live stream configurations using semantic search

Let your agent locate and modify stream settings by matching user intent with this MCP Server. By querying `list_streams` and indexing the configurations, the agent can find the right stream to update even if you don't remember the exact ID. Once the correct stream is identified, the agent calls `update_stream` or `delete_stream` to apply changes. This turns complex API management into a natural, conversational experience.

Setup guide

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

LlamaIndex calls tools like `list_assets` or `get_viewership_metrics` and converts the JSON outputs into Document objects. These documents are then split, embedded, and stored in your vector database, making your video data searchable in real time.

Yes, you can query `get_usage_metrics` to retrieve data on total minutes transcoded and delivered. Your LlamaIndex agent can then index this financial data to help you track costs and predict future infrastructure spend.

The agent can query `get_playback_info` to retrieve the active playback URLs and metadata. By comparing this live data with indexed configuration files, the agent can pinpoint misconfigured streams and recommend the exact fix.

Yes, you can use LlamaIndex's `allowed_tools` filter when loading the MCP server. This lets you restrict your agent to read-only tools like `get_asset` and `list_streams` while blocking destructive tools like `delete_stream`.

Yes, the server processes all API keys, stream configurations, and viewership metrics locally within an isolated V8 sandbox. No video data or credentials are sent to external third parties, ensuring your operational metrics remain private.

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