How to Use the Dyte MCP in LangChain

Q: Can a LangChain agent manage Dyte participants dynamically?

Yes, the agent uses listparticipants to check active users and addparticipant to invite new ones. Each tool call is tracked in LangSmith so you can debug the execution order.

Q: How does Dyte handle recording storage in LangChain chains?

You pass storage configurations directly to startrecording within the agent's tool call parameters. Once done, the agent calls getrecording to pass the file path to subsequent data processing nodes.

Get your LangChain agents spinning up video calls and managing live streams with zero manual glue code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dyte MCP to LangChain

Create your Vinkius account to connect Dyte 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 Dyte with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run dynamic video sessions inside LangChain chains

`create_meeting` is the tool that lets your LangChain agent initialize video rooms on demand based on conversation events. The agent evaluates the dialogue context, decides when a live sync is necessary, and triggers the room creation instantly. Once the room is live, the chain feeds the resulting session ID into `add_participant` to onboard users. You get clean LangSmith traces showing the exact latency and inputs of each step in the meeting setup sequence.

Control live recordings with sequential tool steps

`start_recording` allows your LangChain agent to archive active video sessions based on runtime triggers. The agent monitors the meeting state and triggers the recording without requiring manual intervention from your backend. When the session wraps up, the agent calls `stop_recording` and fetches the asset details via `get_recording`. This output pipes directly into the next chain link, letting you run post-meeting transcriptions or analysis pipelines.

Automate live stream events from agent chains

`start_livestream` broadcasts your active Dyte meetings to external platforms directly through your agent's decision loop. The agent evaluates the audience size or event type before initiating the broadcast. If the event ends, the agent invokes `stop_livestream` and cleans up the active session. This MCP Server integration handles the API calls so your agent can focus on managing the broadcast lifecycle.

Setup guide

Set up Dyte 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 Dyte 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({
    "dyte-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 Dyte 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 Dyte. 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 Dyte 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 Dyte MCP in LangChain

Install langchain-mcp-adapters and pass the Vinkius HTTP endpoint to MultiServerMCPClient. Then, extract the tools with get_tools() and pass them to your agent constructor.

Yes, the agent uses list_participants to check active users and add_participant to invite new ones. Each tool call is tracked in LangSmith so you can debug the execution order.

You pass storage configurations directly to start_recording within the agent's tool call parameters. Once done, the agent calls get_recording to pass the file path to subsequent data processing nodes.

You can aggregate multiple servers using MultiServerMCPClient. This lets your agent coordinate video meetings alongside databases or other messaging APIs in a single reasoning loop.

Vinkius runs the MCP server in an isolated V8 sandbox where your API keys are never exposed to the client. Only ephemeral session metadata like meeting IDs and participant tokens pass through the secure proxy.

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