How to Use the 100ms MCP in LangChain

Q: How do I configure the 100ms integration in LangChain?

You install the langchain-mcp-adapters package and connect to the 100ms MCP Server via the Vinkius endpoint. From there, you call gettools() and pass them directly to your agent constructor.

Q: How does LangChain handle 100ms participant removal?

Your agent uses removepeer to execute the action via the MCP integration. It extracts the session ID and peer ID from the current context and passes these parameters directly to the tool during its reasoning loop.

Q: Can a LangChain agent list all 100ms video rooms and recordings?

The agent executes listrooms to find the correct room ID, then calls listrecordings to locate the files. This allows your chains to handle complex asset retrieval without hardcoded IDs.

Build multi-step video operations into your LangChain agents to manage live rooms and sessions automatically.

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 LangChain

Create your Vinkius account to connect 100ms to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain room creation with configuration updates in LangChain

Your agent uses `create_room` to spin up a video room from a natural language request and instantly configure its settings. It pipes that output directly into `update_room` to set custom templates or recording preferences in one clean sweep. This chain removes the manual step of copying IDs between API calls. Your agent handles the sequential logic, logging every input and output in LangSmith so you can trace the exact parameters passed to the 100ms API.

Monitor active sessions with LangChain MCP Server tools

Your agent monitors active sessions using `list_sessions` and automatically boots unauthorized attendees. By calling `list_peers`, the agent evaluates who is in the room and uses `remove_peer` to kick anyone who shouldn't be there. You stop writing custom cron jobs to police your video rooms. The agent runs this loop autonomously, evaluating the state of your live calls and taking corrective action based on real-time participant lists.

Generate post-meeting reports using session history

Your agent pulls down past meeting metadata using `list_sessions` and recording URLs to compile summaries. It identifies completed meetings and uses `list_recordings` to fetch the cloud storage links for the team. This stops the post-meeting scramble for links and attendee lists. The agent aggregates the raw data and hands it off to your LLM chain to draft clean, accurate follow-up emails.

Setup guide

Set up 100ms MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes 100ms tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "100ms-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent 100ms transactions"
    })
    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 LangChain

You install the `langchain-mcp-adapters` package and connect to the 100ms MCP Server via the Vinkius endpoint. From there, you call `get_tools()` and pass them directly to your agent constructor.

Yes, every tool call is tracked in your LangSmith dashboard automatically. You see the latency, payload size, and exact JSON responses returned from the server for tools like `create_room` or `list_sessions`.

Your agent uses `remove_peer` to execute the action via the MCP integration. It extracts the session ID and peer ID from the current context and passes these parameters directly to the tool during its reasoning loop.

The agent executes `list_rooms` to find the correct room ID, then calls `list_recordings` to locate the files. This allows your chains to handle complex asset retrieval without hardcoded IDs.

Your video room IDs and participant lists are processed inside a secure V8 Isolate Sandbox. Your session details run inside an MCP sandbox using a secure V8 Isolate, meaning your API credentials and session details are never retained.

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