How to Use the Grain MCP in OpenAI Agents SDK

Q: How do I connect Grain to my OpenAI Agents SDK pipeline?

You install the openai-agents package and configure the MCPServerStreamableHttp client with your Vinkius endpoint. Vinkius handles the underlying MCP connection, so your agent can immediately call tools like listrecordings during execution.

Q: Does the Grain MCP server support tool handoffs in OpenAI Agents SDK?

Absolutely. You can have a routing agent run searchrecordings and then pass the target ID to a specialized analysis agent that calls gettranscript for deep processing.

Feed meeting transcripts and action items directly to your OpenAI Agents SDK pipelines without manual API wiring.

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 OpenAI Agents SDK

Create your Vinkius account to connect Grain to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate CRM updates using the OpenAI Agents SDK

Stop wasting time copy-pasting call notes into your CRM. Let your agent grab the raw text straight from the source. When you wire `get_transcript` and `get_action_items` into your OpenAI Agents SDK setup, your system automatically parses what happened in a call and updates your pipeline. The SDK handles agent handoffs like a pro. One agent can extract the raw text while a specialized CRM-writing agent commits the clean data, skipping messy custom API glue entirely.

Search and filter workspace recordings

Your agent can hunt through thousands of hours of audio and video using `search_recordings` to find specific client mentions. It uses the Grain MCP server to index and locate files without downloading massive media files first. Once found, the agent uses `list_highlights` or `get_insights` to pull specific moments. This keeps your context window clean because you only feed the model the exact snippets it needs to answer a user query.

Process external videos on the fly

When a user drops a video link into your agent's chat, the system can immediately process it using `upload_video`. This tells Grain to ingest the external media and generate a structured layout of the discussion. The agent can then monitor the upload status and call `get_recording` once it finishes. It gives your OpenAI Agents SDK system the ability to analyze video files from external drives or public links without building your own media processing pipeline.

Setup guide

Set up Grain MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Grain tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Grain tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Grain tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Grain Agent",
            instructions="You have access to Grain tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You install the `openai-agents` package and configure the `MCPServerStreamableHttp` client with your Vinkius endpoint. Vinkius handles the underlying MCP connection, so your agent can immediately call tools like `list_recordings` during execution.

Yes, but you should avoid passing raw files directly to the model. Use `get_insights` or `list_highlights` first to let the Grain MCP server pre-digest the meeting data, saving your context window.

Absolutely. You can have a routing agent run `search_recordings` and then pass the target ID to a specialized analysis agent that calls `get_transcript` for deep processing.

You can manage tool exposure directly in your Vinkius dashboard or filter the tool list programmatically during the SDK initialization before passing them to your agent constructor.

Your audio files and transcripts remain secure within Grain's infrastructure. Vinkius runs this MCP server in a zero-trust, ephemeral V8 isolate, meaning your raw meeting data is never cached or stored on the integration layer.

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