How to Use the 100ms MCP in OpenAI Agents SDK

Build production-ready video operations agents with OpenAI Agents SDK that manage 100ms rooms and active sessions safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 100ms MCP to OpenAI Agents SDK

Create your Vinkius account to connect 100ms 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 100ms with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage live sessions with OpenAI guardrails

Your multi-agent system can monitor active video calls and intervene automatically. When a moderator agent detects a policy violation, it triggers a handoff to an enforcement agent that calls `remove_peer` to kick the disruptive participant out of the session. You stop writing custom moderation backends. The agent checks `list_peers` to identify the user, validates the action against your defined safety constraints, and executes the removal with full tracing visible in your OpenAI dashboard.

Provision 100ms rooms dynamically

Agents can spin up new video environments on demand without human oversight. An onboarding agent reads a user request, fires off `create_room` to generate the space, and immediately returns the join credentials to the client. Manual room creation disappears from your operations queue. If settings need adjustments later, the agent just hits `update_room` to tweak capacities or recording toggles, keeping everything within your strict production guardrails.

Audit video sessions and recordings

A specialized compliance agent can pull historical data across your entire video infrastructure. It grabs data via `list_sessions` to see who attended past meetings and pulls cloud storage links using `list_recordings`. You skip the manual dashboard digging. The agent cross-references room IDs, fetches session metadata through `get_session`, and dumps a formatted audit report directly into your logging pipeline.

Setup guide

Set up 100ms 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 100ms tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives 100ms tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate 100ms 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="100ms Agent",
            instructions="You have access to 100ms 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 100ms. 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 100ms 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 100ms MCP in OpenAI Agents SDK

Install the openai-agents package via pip and set up the connection. You pass the server URL into MCPServerStreamableHttp and inject it directly into your Agent constructor using the mcp_servers parameter.

Yes, it auto-discovers every available tool. Set cacheToolsList=True in your configuration to speed up initialization when the agent loads the room management commands.

Your agent can definitely boot someone if you give it permission. It calls `list_peers` to find the specific participant ID, then executes `remove_peer` to drop them from the active session.

You instruct the agent to search by specific criteria. It uses `list_recordings` and applies filters for particular room IDs or recording statuses to find exactly what you need.

Your video session metadata stays completely isolated. The integration runs inside a V8 Isolate Sandbox, meaning the agent reads your active peer lists and room settings ephemerally without retaining a single byte of meeting 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