How to Use the 100ms MCP in AutoGen

Q: How do I register 100ms tools with AutoGen agents?

You install autogen-extmcp and use mcpservertools to load the 100ms MCP Server tools. Pass the resulting tool list to your AssistantAgent constructor to give it video management capabilities.

Q: Can an AutoGen agent kick users from a 100ms session?

Yes, an agent can call removepeer after verifying the peer ID and session ID. This can be triggered autonomously when the security agent flags a participant policy violation.

Q: How do AutoGen agents collaborate on 100ms room creation?

One agent can call createroom to generate the meeting space, and another agent can call updateroom to apply specific corporate templates. The agents negotiate the payload before firing the MCP request.

Q: Can AutoGen agents audit past 100ms sessions?

Your agents can call listsessions and getsession to audit participant attendance and duration. The auditing agent compiles this data and presents a report to the coordinator agent.

Coordinate multi-agent debates in AutoGen to manage room security and video configurations.

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 AutoGen

Create your Vinkius account to connect 100ms to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate room security via multi-agent consensus

Your moderator agent calls `list_peers` to fetch the current participant list while collaborating with a security agent. The security agent cross-references it with your guest database to detect anomalies. If an unauthorized user is found, the agents debate the risk and execute `remove_peer` to kick them. This removes the need for human moderators to constantly watch active video sessions.

Coordinate room setup using AutoGen MCP Server tools

Your provisioning agent proposes a layout with `create_room` while negotiating settings with a compliance agent. The compliance agent checks if recording is required and triggers `update_room` to enforce it. You prevent unrecorded or misconfigured meetings from starting. The agents handle the negotiation and configuration in the background before handing the room URL to the host.

Resolve recording conflicts through agent debate

Your compliance agent calls `list_recordings` to find old files while the storage agent calculates active footprints. They analyze the metadata to identify files that exceed your retention policy. They decide which recordings to archive or flag based on your team's budget rules. This automated negotiation keeps your cloud storage clean without manual intervention.

Setup guide

Set up 100ms MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes 100ms tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="100ms_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent 100ms data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="100ms_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent 100ms data")
    print(result.messages[-1].content)

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 AutoGen

You install `autogen-ext[mcp]` and use `mcp_server_tools` to load the 100ms MCP Server tools. Pass the resulting tool list to your `AssistantAgent` constructor to give it video management capabilities.

Yes, an agent can call `remove_peer` after verifying the peer ID and session ID. This can be triggered autonomously when the security agent flags a participant policy violation.

One agent can call `create_room` to generate the meeting space, and another agent can call `update_room` to apply specific corporate templates. The agents negotiate the payload before firing the MCP request.

Your agents can call `list_sessions` and `get_session` to audit participant attendance and duration. The auditing agent compiles this data and presents a report to the coordinator agent.

All tool execution is isolated within a zero-trust V8 Isolate Sandbox running the MCP server. Your room configurations and participant IDs are processed ephemerally, ensuring no sensitive data remains in the execution 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