How to Use the Volcengine RTC MCP in OpenAI Agents SDK

Q: Can I manage multiple calls using Volcengine RTC and OpenAI Agents SDK?

Yep. Your agent can check for all live rooms by calling getactiverooms. This gives you a central view of where your resources are active. It lets the agent switch context between different calls as needed.

Q: Is user removal secure when using Volcengine RTC and OpenAI Agents SDK?

The kickuser tool allows instant participant removal. Your agent executes this action directly, ensuring the user is removed from the designated room. This direct control helps maintain a safe call environment.

Manage real-time video calls using your OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Volcengine RTC MCP to OpenAI Agents SDK

Create your Vinkius account to connect Volcengine RTC to OpenAI Agents SDK 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 Volcengine RTC with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Call Participants

You can list every active room in Volcengine with the `get_active_rooms` tool. Need to know who's actually talking? Use `get_room_users` to retrieve a current roster of participants. If someone causes trouble, you don't have to manually intervene. The `kick_user` function lets your agent immediately remove a participant from the call.

Manage Call Media Streams

Audio and video streams need controlling when things go south. Your agent can mute specific outputs—either audio or video—using `mute_stream`. When you're done, simply bring everything back to life with `unmute_stream`. This gives your production agent system granular control over call quality, ensuring the right media is always active.

Control Recording and Transcoding

Need a permanent record of what happened? Call `start_cloud_record` to initiate Volcengine Cloud Recording. When you're done with the session, use `stop_cloud_record` to wrap it up. Beyond recording, your agent manages media transformation. It can start transcoding streams using `start_transcode` and halt that process when finished with `stop_transcode`.

Setup guide

Set up Volcengine RTC MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Volcengine RTC tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Volcengine RTC tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Volcengine RTC tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Volcengine RTC Agent",
            instructions="You have access to Volcengine RTC tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Volcengine RTC. 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 Volcengine RTC 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 Volcengine RTC MCP in OpenAI Agents SDK

The agents use MCP tools to talk directly to your Volcengine RTC setup. This lets you manage calls—like kicking a user or starting a recording—all within an automated workflow. It means your production agent system can handle call administration without needing manual API calls.

This server handles real-time communication metadata, specifically the current state and list of users within an active RTC room. The agent reads this user data to perform actions like kitting a participant. It deals with who is in the call and what media streams are running.

Yep. Your agent can check for all live rooms by calling `get_active_rooms`. This gives you a central view of where your resources are active. It lets the agent switch context between different calls as needed.

Absolutely. You can get deep performance stats for any given room by calling `get_quality_metrics`. This gives visibility into the call's health and quality. This data helps your agent make decisions about whether a call needs intervention.

The `kick_user` tool allows instant participant removal. Your agent executes this action directly, ensuring the user is removed from the designated room. This direct control helps maintain a safe call environment.

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