4,500+ servers built on MCP Fusion
Vinkius
Granola logo
Vinkius
OpenAI Agents SDK logo

How to Use the Granola MCP in OpenAI Agents SDK

Run secure OpenAI Agents SDK pipelines that automatically pull meeting decisions and transcripts from Granola.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Granola MCP on Cursor AI Code Editor MCP Client Granola MCP on Claude Desktop App MCP Integration Granola MCP on OpenAI Agents SDK MCP Compatible Granola MCP on Visual Studio Code MCP Extension Client Granola MCP on GitHub Copilot AI Agent MCP Integration Granola MCP on Google Gemini AI MCP Integration Granola MCP on Lovable AI Development MCP Client Granola MCP on Mistral AI Agents MCP Compatible Granola MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
OpenAI Agents SDK

Connect Granola MCP to OpenAI Agents SDK

Create your Vinkius account to connect Granola 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

Run secure meeting pipelines with OpenAI Agents SDK

The `get_action_items` tool lets your agent pull verified post-meeting tasks directly into your production pipelines. This tool processes the raw meeting text so your agent can update external databases or trigger follow-up tasks without manual data entry. By chaining `get_summary` with your OpenAI agent's built-in guardrails, you ensure that only verified decisions pass to downstream systems. The SDK validates these actions before execution, keeping your production workflows clean and error-free.

Track transcript histories across multi-agent handoffs

The `get_transcript` tool retrieves full transcripts with speaker detection to feed your specialized analysis agents. Your master agent can hand off this raw text to a dedicated summarization agent to isolate specific technical requirements. Using `list_recent` alongside these handoffs lets your agent system maintain constant context without hitting token limits. The OpenAI dashboard traces every single tool call, so you see exactly when and why an agent requested a specific meeting transcript.

Batch process meeting data safely inside the sandbox

The `get_documents_batch` tool retrieves multiple meeting records in a single request to reduce your API latency. This batching mechanism helps your OpenAI agent analyze trends across multiple client calls without making repetitive network requests. Your agent runs these queries through a zero-trust Vinkius MCP Server sandbox. This isolated execution environment ensures your sensitive corporate records remain protected while the agent extracts metadata with `get_metadata`.

Setup guide

Set up Granola 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. 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. 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 Granola tools at runtime.

  3. 3

    Create your Agent

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

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Granola 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="Granola Agent",
            instructions="You have access to Granola tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Granola. 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.

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 Granola MCP in OpenAI Agents SDK

The SDK queries the Vinkius MCP Server endpoint using the MCPServerStreamableHttp client. It automatically registers all 12 tools, including list_documents and get_action_items, with no manual configuration required.
Yes, you can restrict tool execution by applying guardrails inside your agent definition. This prevents the agent from calling tools like search_documents unless specific validation conditions are met.
The SDK processes the text chunk by chunk to avoid exceeding model context windows. The MCP connection allows you to call get_summary first to check if you actually need to fetch the full transcript via get_transcript.
Use the search_documents MCP tool to run a full-text search across your workspace. This returns matching documents immediately, bypassing the need to paginate through the entire document list.
Your meeting transcripts, summaries, and action items are processed inside ephemeral V8 isolates. Vinkius never writes this data to persistent storage, ensuring absolute isolation from other users.

Start using the Granola MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 12 tools

We've already built the connector for Granola. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.