Can I create an action item and assign it to a team member?

Yes! Use `create_action_item` with the title, assignee email, and optional due date. You can also link it to a specific meeting.

How do I get the notes from a specific meeting?

Use `list_notes` with the meeting ID to get all notes linked to that meeting, or `get_note` with a specific note ID for full content.

Can I mark action items as completed via the AI agent?

Absolutely. Use `complete_action_item` with the action item ID to mark it as done.

INSTANT PLUG AND PLAY

Fellow MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 12 tools to Check Fellow Status, Complete Action Item, Create Action Item, and more

Name: Fellow
Availability: InStock
Author: Vinkius

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Fellow through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Use with Your AI Agent

Ask AI about this App Connector for OpenAI Agents SDK

Open in ChatGPT Open in Claude Open in Perplexity

The Fellow app connector for OpenAI Agents SDK is a standout in the Productivity category — giving your AI agent 12 tools to work with, ready to go from day one.

Vinkius delivers Streamable HTTP and SSE to any MCP client

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Fellow Assistant",
            instructions=(
                "You help users interact with Fellow. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Fellow"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Fellow MCP Server

Connect your Fellow workspace to any AI agent and manage your entire meeting workflow through natural conversation.

The OpenAI Agents SDK auto-discovers all 12 tools from Fellow through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Fellow, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Meetings — List and inspect meetings with titles, participants, dates, and agendas.
Notes — Access structured meeting notes and AI-generated summaries.
Action Items — Create, track, and complete action items with assignees and due dates.
Streams — Browse recurring meeting series and their schedules.
Users — List all workspace members and their roles.

The Fellow MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 12 Fellow tools available for OpenAI Agents SDK

When OpenAI Agents SDK connects to Fellow through Vinkius, your AI agent gets direct access to every tool listed below — spanning meeting-management, collaborative-agendas, action-items, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.

check_fellow_status

Verify Fellow API connectivity

complete_action_item

Mark an action item as completed

create_action_item

Optionally link it to a meeting, assign to a user by email, and set a due date. Create a new action item from a meeting

get_action_item

Get details of a specific action item

get_meeting

Get full details of a specific meeting

get_note

Get full content of a specific note

get_stream

Get details of a specific meeting stream

list_action_items

Optionally filter by status: "pending", "completed", or "archived". List action items from meetings

list_meetings

List recent meetings from Fellow

list_notes

Optionally filter by a specific meeting ID to get notes for that meeting only. List meeting notes

list_streams

List all meeting streams (recurring series)

list_users

List all users in the Fellow workspace

Connect Fellow to OpenAI Agents SDK via MCP

Follow these steps to wire Fellow into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from Fellow

Why Use OpenAI Agents SDK with the Fellow MCP Server

OpenAI Agents SDK provides unique advantages when paired with Fellow through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Fellow + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Fellow MCP Server delivers measurable value.

Automated workflows: build agents that query Fellow, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Fellow, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Fellow tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Fellow to resolve tickets, look up records, and update statuses without human intervention

Example Prompts for Fellow in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Fellow immediately.

"Show me my recent meetings in Fellow."

"Create an action item 'Send proposal to client' and assign it to sarah@team.com with a due date of May 10."

"List all pending action items."

Troubleshooting Fellow MCP Server with OpenAI Agents SDK

Common issues when connecting Fellow to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Fellow + OpenAI Agents SDK FAQ

Common questions about integrating Fellow MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.