How to Use the Agora MCP in LangChain

Q: Can LangChain trace my Agora cloud recording calls?

Yes, every execution of startcloudrecording or stopcloudrecording shows up inside LangSmith. You get full visibility into latency, payload sizes, and raw JSON responses.

Q: Can my agent monitor active whiteboard rooms?

Yes, the agent calls listwhiteboardrooms to fetch active sessions. It then cross-references this list with live calls to prune stale whiteboard rooms.

Build multi-step LangChain pipelines that manage Agora voice, video, and whiteboard sessions based on real-time API feedback.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agora MCP to LangChain

Create your Vinkius account to connect Agora 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 Agora with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step Agora cloud recording chains in LangChain

`acquire_cloud_recording` gets the mandatory resource ID from Agora before your LangChain agent triggers any recording. Your agent uses this ID to execute `start_cloud_recording` and then monitors progress via `query_cloud_recording`. LangSmith traces the exact latency of these API calls as they execute in your sequence. If a recording fails, the chain catches the error, inspects the status, and retries with a fresh resource ID.

Track live Agora usage stats inside LangChain pipelines

`get_usage_stats` retrieves concrete data consumption metrics for any specific project ID in your account. The agent feeds these metrics directly into downstream LangChain tools to alert your team when bandwidth spikes. Feed the output of `list_active_calls` into a decision node to automatically spin down inactive projects. This builds closed-loop infrastructure that sweeps up dead resources without you writing custom cleanup scripts.

Let LangChain agents spin up Agora projects via MCP

`create_project` spins up brand new Agora developer environments on the fly. The agent instantly reads the returned credentials and uses `get_project_details` to verify that the API keys are active. Since LangChain aggregates multiple servers, your agent hands these new credentials straight to a database tool in the exact same chain. This updates your application database in a single run.

Setup guide

Set up Agora 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 Agora 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({
    "agora-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 Agora 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 Agora. 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 Agora 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 Agora MCP in LangChain

Install the langchain-mcp-adapters package and feed the server URL to MultiServerMCPClient. Call client.get_tools() and pass them directly to your agent constructor to run live video operations.

Yes, every execution of start_cloud_recording or stop_cloud_recording shows up inside LangSmith. You get full visibility into latency, payload sizes, and raw JSON responses.

By default, the MCP adapter is stateless, but use client.session() to keep Agora project details persistent. This lets your agent remember which project ID it created during previous steps.

Yes, the agent calls list_whiteboard_rooms to fetch active sessions. It then cross-references this list with live calls to prune stale whiteboard rooms.

Vinkius runs the MCP Server inside a zero-trust, ephemeral V8 Isolate sandbox. Your project credentials and live session logs never persist on our disks or leak to other users.

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