How to Use the Grain MCP in LangChain

Q: Can LangChain agents search through past Grain recordings?

Yes, your agent can use the searchrecordings tool to find specific keywords across your history. It can then pull the exact text using gettranscript to answer user queries.

Q: Can I extract action items from a meeting using LangChain?

Yes, your agent can run getactionitems on a specific recording ID to retrieve a structured list of tasks. It can then immediately pass those tasks to the next chain in your pipeline.

Feed real-time meeting transcripts and action items directly into your LangChain pipelines with this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grain MCP to LangChain

Create your Vinkius account to connect Grain 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 Grain with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain meeting insights with LangChain agents

Your LangChain agent can now run multi-step reasoning over raw conversation data. By calling `get_transcript` first, the agent can parse the text, find context, and then trigger `get_insights` to build a structured summary. You don't need to write custom parsing code or manage API endpoints yourself because the MCP Server handles the raw payload delivery. This workflow lets you feed meeting data directly into other LangChain tools or vector databases. If an agent finds a critical follow-up, it can immediately use `get_action_items` to pull the specific tasks and assign them to your team in a downstream step.

Track tool execution via LangSmith

Debugging agentic workflows gets messy when dealing with large audio files and transcripts. With this integration, every call to `list_recordings` or `search_recordings` is fully visible in your LangSmith dashboard. You see the exact latency, token count, and inputs for every single tool execution. This visibility helps you optimize how your LangChain chains interact with meeting data. You will catch failing calls or rate limits instantly when your agent executes `upload_video` or pulls large payloads with `get_recording`.

Build multi-server agent pipelines

LangChain excels at combining multiple tools into a cohesive agent. You can pair this connection with database or CRM configurations to automate post-meeting updates. For example, your agent can look up workspace users with `list_workspace_members` and match them to CRM records. The setup is straightforward using the LangChain MCP adapters. Your agent will decide when to call `list_shared_clips` or `list_tags` based on the conversation context, creating a fully autonomous workflow.

Setup guide

Set up Grain 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 Grain 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({
    "grain-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 Grain 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 Grain. 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 Grain 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 Grain MCP in LangChain

Install langchain-mcp-adapters and langgraph via pip. Then, define the client using MultiServerMCPClient with the Vinkius transport URL and pass the tools directly to your agent constructor.

Yes, your agent can use the `search_recordings` tool to find specific keywords across your history. It can then pull the exact text using `get_transcript` to answer user queries.

The server is stateless by default to keep operations fast. If your LangChain agent needs to maintain context across multiple tool calls, use client.session() to manage the persistent connection state.

Yes, your agent can run `get_action_items` on a specific recording ID to retrieve a structured list of tasks. It can then immediately pass those tasks to the next chain in your pipeline.

Your meeting transcripts and raw recordings are protected by the Vinkius V8 sandboxed environment. Your API tokens are managed securely, meaning your LangChain agent accesses the data through a single authenticated endpoint without exposing raw credentials.

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