How to Use the Magic Minutes MCP in LangChain

Q: How do I connect the Magic Minutes MCP Server to LangChain?

Install langchain-mcp-adapters. Then instantiate a MultiServerMCPClient pointing to the Vinkius endpoint. Call client.gettools() and pass the array to your agent.

Q: Can LangChain agents read past Magic Minutes agendas?

Yes. Your agent calls listmeetings to find the ID, then hits getmeetingdetails for the agenda. The agent handles the context window.

Q: Why is my LangChain agent failing to assign Magic Minutes tasks?

You likely forgot to give the agent access to listcontacts. The agent needs the correct user ID before it can successfully call createtask. Check your LangSmith traces to confirm the exact tool inputs.

Build multi-step meeting analysis pipelines with the Magic Minutes MCP Server in LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Magic Minutes MCP to LangChain

Create your Vinkius account to connect Magic Minutes 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 Magic Minutes with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Meeting Data in LangChain

The `get_meeting_minutes` tool pulls raw meeting transcripts straight into your LangChain ReAct agents via the MCP standard. You build the pipeline. The agent reads the agenda, identifies the decisions made, and passes that text to the next node in your chain. Tracing happens automatically through LangSmith. You see exactly how many tokens the agent burned while parsing attendees with `list_meeting_attendees`. If a reasoning step fails, you check the logs, adjust the prompt, and run the chain again.

Automate Task Distribution

Calling `create_task` turns an unstructured conversation into tracked action items. Your agent looks at the meeting summary, finds commitments, and fires off tasks. It then uses `list_contacts` to assign the right person to each job. This setup thrives on intermediate results. The output from checking `get_task_details` dictates what the agent does next. You write the logic, and the MCP Server handles the actual data reads and writes.

Monitor Pipeline Health

The `check_api_health` tool gives your application a direct pulse check on the API. Before running a heavy, token-intensive summarization chain, your agent pings the endpoint to confirm connectivity. Active webhooks get mapped out via `list_webhooks`. You track where the data goes after the chain completes. Everything stays observable, and you never guess why a meeting summary failed to reach its destination.

Setup guide

Set up Magic Minutes 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 Magic Minutes 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({
    "magic-minutes-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 Magic Minutes 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 Magic Minutes. 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 Magic Minutes 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 Magic Minutes MCP in LangChain

Install `langchain-mcp-adapters`. Then instantiate a `MultiServerMCPClient` pointing to the Vinkius endpoint. Call `client.get_tools()` and pass the array to your agent.

Yes. Your agent calls `list_meetings` to find the ID, then hits `get_meeting_details` for the agenda. The agent handles the context window.

You likely forgot to give the agent access to `list_contacts`. The agent needs the correct user ID before it can successfully call `create_task`. Check your LangSmith traces to confirm the exact tool inputs.

The server itself is stateless. You manage persistent context by calling `client.session()` within your framework setup.

Transcripts and attendee lists process through an ephemeral V8 Isolate Sandbox. The server executes the read operation, returns the text to your environment, and destroys the instance entirely. Zero data persists on the network.

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