How to Use the Fellow MCP in OpenAI Agents SDK

Q: Can my Fellow workspace tasks be closed automatically by my OpenAI Agents SDK system?

Yes, the agent uses completeactionitem to mark tasks finished. We recommend adding a validation step in your agent logic to prevent tasks from being closed prematurely.

Q: Can the agent delete meeting notes without confirmation?

The deletenote tool requires explicit confirmation before execution. You should configure your agent's guardrails to prompt a human operator before triggering this destructive action.

Get your OpenAI Agents SDK systems managing meetings, tracking action items, and parsing transcripts directly from your production pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fellow MCP to OpenAI Agents SDK

Create your Vinkius account to connect Fellow 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 Fellow with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Action Item Tracking with OpenAI Agents SDK

The `list_action_items` tool lets your agent pull active tasks across all workspace meetings to keep your team aligned. Once a task is done, the agent calls `complete_action_item` to mark it finished, or uses `archive_action_item` to clean up the board. This keeps your task database clean without manual human updates. You get direct control over the task lifecycle. By inspecting specific tasks with `get_action_item`, your agent validates execution before closing tickets. This prevents false positives and ensures developers actually finished the work before the system archives it.

Meeting Note Management

The `list_notes` tool acts as the entry point for your agent to search and browse all workspace documentation. When it locates the target meeting, it uses `get_note` to extract decisions, agenda items, and context. For cleanup operations, the agent can call `delete_note` after receiving explicit human confirmation. This workflow ensures stale or redundant documentation is removed without risking accidental data loss. This MCP Server setup handles the authentication layer so your agents only focus on the text.

Transcript and Recording Processing

The `list_recordings` tool exposes your captured meeting history directly to your agent workflows. Your agent uses `get_recording` to fetch metadata and then calls `get_transcript` to extract raw text for analysis. This setup turns hours of audio into searchable data. If a recording is no longer needed, the agent runs `delete_recording` to manage storage. By pairing this MCP tool with OpenAI's tracing dashboard, you monitor exactly how and when audio files are processed.

Setup guide

Set up Fellow 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 Fellow tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fellow 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="Fellow Agent",
            instructions="You have access to Fellow 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 Fellow. 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 Fellow 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 Fellow MCP in OpenAI Agents SDK

Install the SDK and use the streamable HTTP server parameter with your Vinkius endpoint. Pass this server instance to your agent constructor to auto-discover all twelve tools instantly.

Yes, the agent uses `complete_action_item` to mark tasks finished. We recommend adding a validation step in your agent logic to prevent tasks from being closed prematurely.

Vinkius manages the authentication handshake. Your agent calls `get_current_user` to verify the connected profile, removing the need to manage raw API tokens inside your application code.

The `delete_note` tool requires explicit confirmation before execution. You should configure your agent's guardrails to prompt a human operator before triggering this destructive action.

All transcripts, recordings, and notes remain inside Fellow's secure infrastructure. This MCP connection ensures your sensitive meeting audio and text data never leak to other environments.

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