How to Use the Whereby MCP in LangChain

Q: How can I list all current and pending calls using the Whereby MCP Server with LangChain?

You call listactivemeetings. This simple tool gives you a definitive rundown of every room that's up or waiting to start. Your agent gets this list, letting it decide which rooms need attention next in the chain.

Q: Whereby: If I need to know what recordings are available, how does LangChain access that data?

The chain uses listcloudrecordings to see everything. From there, it can drill down and fetch specific download links and metadata by calling getrecordingdetails. This output is perfect for adding to a database record.

Q: Whereby/LangChain: What if I need to delete a meeting room?

You just call deletemeetingroom. It terminates the session right away. Because this action is irreversible, your chain must handle the confirmation step before proceeding.

Build complex meeting management pipelines with LangChain's advanced reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Whereby MCP to LangChain

Create your Vinkius account to connect Whereby 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 Whereby with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Meetings and Rooms

Need to spin up a temporary call space? Your agent calls `create_meeting_room` by providing the ISO 8601 end date and whether it's 'normal' or a 'group.' The output, which contains the room details, can then feed into another step of your chain for logging or notification. Alternatively, if you need to clean up, `delete_meeting_room` terminates the session immediately. This allows your multi-step pipeline to manage the entire lifecycle of a meeting space.

Control Branding and Themes

When your chain needs to standardize video appearances, it can first check existing styles with `get_room_theme`. Then, if necessary, it uses `update_room_theme`, feeding the room name and a hex color code straight into the operation. You'll find you also have `reset_room_theme` if you just want to revert everything back to default branding. This level of control means your agent can programmatically enforce brand guidelines across multiple meetings, treating theme management like any other data point in its workflow.

Process Recordings and Data

The chain doesn't stop at live calls. It handles post-meeting tasks too. Use `list_cloud_recordings` to see what files are stored, then pull the necessary download links using `get_recording_details`. This output can be passed directly into a vector store for indexing later on. If you need to remove data permanently, `delete_cloud_recording` handles that. It's an irreversible action, so your agent must confirm this step before running it.

Setup guide

Set up Whereby 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 Whereby 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({
    "whereby-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 Whereby 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 Whereby. 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 Whereby 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 Whereby MCP in LangChain

You call `list_active_meetings`. This simple tool gives you a definitive rundown of every room that's up or waiting to start. Your agent gets this list, letting it decide which rooms need attention next in the chain.

Yeah, you can. First, your agent checks a room's current style with `get_room_theme`. Then it executes `update_room_theme`, supplying the exact hex code and room name needed for the change.

The chain uses `list_cloud_recordings` to see everything. From there, it can drill down and fetch specific download links and metadata by calling `get_recording_details`. This output is perfect for adding to a database record.

You just call `delete_meeting_room`. It terminates the session right away. Because this action is irreversible, your chain must handle the confirmation step before proceeding.

This MCP Server handles room names, visual theme settings (colors and logos), and general meeting metadata. The agent interacts with these textual and hexadecimal configuration values.

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