How to Use the Livepeer (Decentralized Video) MCP in Pydantic AI

Q: How do I handle asynchronous tasks like transcoding in Livepeer (Decentralized Video) using Pydantic AI?

The agent polls gettask asynchronously to monitor the transcoding status. It yields control back to your application until the decentralized network completes the job.

Q: Where are my stream keys and viewer analytics stored?

All stream credentials and metrics fetched via getrealtimeviewership pass through memory only. Vinkius runs the server in an ephemeral sandbox, ensuring no persistent storage of your telemetry data.

Build type-safe video pipelines with Pydantic AI to manage streams and track analytics on Livepeer.

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 Pydantic AI

Create your Vinkius account to connect Livepeer (Decentralized Video) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage live streams with Pydantic AI validation

Creating a stream begins with calling `create_stream` to receive verified connection details. The agent validates the returned stream keys and ingest URLs against strict Pydantic models before passing them to your frontend. This prevents malformed stream configurations from breaking your player. If you need to stop a broadcast, the agent executes `terminate_stream` and verifies the final stream state before closing the session.

Secure asset ingestion using an MCP Server

The `request_asset_upload` tool returns a validated upload URL for your raw video files. Your agent tracks the upload progress by calling `get_task` and parsing the response with strict type guarantees. Using an MCP Server ensures that every step of the transcoding pipeline is type-checked. If the network returns unexpected metadata during `create_transcode_job`, the framework catches it immediately, preventing silent database corruption.

Generate verified stream clips on the fly

Creating short highlights from a live broadcast is handled by the `create_clip` tool. The agent specifies the exact start and end times, then validates the resulting video asset metadata using `get_asset`. This automated clipping pipeline runs with zero human intervention. You get clean, structured clip objects that are immediately ready for distribution to your social media channels.

Setup guide

Set up Livepeer (Decentralized Video) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "livepeer-decentralized-video-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Livepeer (Decentralized Video) tools.",
)

result = await agent.run("List recent Livepeer (Decentralized Video) transactions")
print(result.output)

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 Pydantic AI

The framework wraps all tool responses in Pydantic models. If `get_playback_info` returns unexpected fields, the agent raises a validation error immediately.

Yes, the framework is model-agnostic. You can connect your local model to the MCP Server to manage streams without relying on external LLM APIs.

The agent polls `get_task` asynchronously to monitor the transcoding status. It yields control back to your application until the decentralized network completes the job.

The integration supports both Streamable HTTP and SSE transports. You pass the MCP server URL to the unified toolset class to establish a persistent, secure connection.

All stream credentials and metrics fetched via `get_realtime_viewership` pass through memory only. Vinkius runs the server in an ephemeral sandbox, ensuring no persistent storage of your telemetry data.

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