How do I create a Mux API Token?

Go to the Mux Dashboard, navigate to Settings > API Tokens, and click 'Create new token'. Ensure you copy the Token Secret immediately as it will only be shown once.

What format should the asset URL be?

The URL must be publicly accessible and point directly to a video file (e.g., MP4, MOV). Mux will then fetch and process the file from that location.

Is the analytics data real-time?

Yes, the `get_recent_views` tool retrieves near real-time data about video views occurring in your account.

Mux MCP Server for OpenAI Agents SDK 11 tools — connect in under 2 minutes

Name: Mux
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 11 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Mux through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Mux Assistant",
            instructions=(
                "You help users interact with Mux. "
                "You have access to 11 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Mux"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Mux MCP Server

Connect your Mux Video account to your AI agent and take full control of your video infrastructure and streaming workflows through natural conversation.

The OpenAI Agents SDK auto-discovers all 11 tools from Mux through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Mux, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Asset Management — List all video assets and get real-time status updates, durations, and playback IDs.
Asset Creation — Create new video assets instantly by providing a public URL to your source file.
Live Streaming — Access and monitor your live stream configurations and their current status.
Direct Uploads — Create secure upload sessions for uploading video files directly.
Video Analytics — Get recent video view metrics to track your content's reach.
Deep Inspection — Fetch complete metadata for specific assets or live streams using their unique IDs.

The Mux MCP Server exposes 11 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Mux to OpenAI Agents SDK via MCP

Follow these steps to integrate the Mux MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 11 tools from Mux

Why Use OpenAI Agents SDK with the Mux MCP Server

OpenAI Agents SDK provides unique advantages when paired with Mux through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Mux + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Mux MCP Server delivers measurable value.

Automated workflows: build agents that query Mux, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Mux, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Mux tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Mux to resolve tickets, look up records, and update statuses without human intervention

Mux MCP Tools for OpenAI Agents SDK (11)

These 11 tools become available when you connect Mux to OpenAI Agents SDK via MCP:

create_asset

Create a new video asset

create_direct_upload

Create a direct upload session

create_live_stream

Create a new live stream

delete_asset

Delete a video asset

delete_live_stream

Delete a live stream

get_asset

Get specific asset details

get_live_stream

Get specific live stream details

get_recent_views

Get recent video views analytics

list_assets

List Mux video assets

list_direct_uploads

List direct video uploads

list_live_streams

List Mux live streams

Example Prompts for Mux in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Mux immediately.

"List all my video assets and show their status."

"Create a new video asset from https://example.com/video.mp4."

"Check recent views for my videos."

Troubleshooting Mux MCP Server with OpenAI Agents SDK

Common issues when connecting Mux to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Mux + OpenAI Agents SDK FAQ

Common questions about integrating Mux MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.