How to Use the Fellow MCP in OpenAI Agents SDK

Q: Can an OpenAI Agents SDK agent assign Fellow tasks to specific users?

Yes, the agent uses listusers to find the target email address and then calls createactionitem to assign the task. This flow runs through your SDK's guardrails to prevent unauthorized assignments.

Q: What is the best way to manage Fellow rate limits in the OpenAI Agents SDK?

Enable cacheToolsList in your OpenAI Agents SDK configuration to avoid redundant schema requests. This keeps tool discovery fast and saves your rate limits for actual data calls like getnote.

Q: Can I use multiple specialized agents to manage meeting notes?

Yes, you can set up one agent to read agendas using listmeetings and hand off to a second agent that updates tasks via completeactionitem. The OpenAI Agents SDK handles these agent handoffs natively.

Build OpenAI Agents SDK systems that update action items, fetch notes, and manage meeting streams with built-in execution guardrails.

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

Control Fellow Action Items with OpenAI Agents SDK

Managing task execution requires rigid validation before execution, which is why this MCP Server exposes `create_action_item` and `complete_action_item` directly to your agent's runtime. The agent automatically discovers these tools and executes updates only after passing your SDK's built-in guardrails. Your production system uses `get_action_item` to inspect task states and verify completion metrics. Tracing these tool calls on the OpenAI dashboard gives you a clear log of every meeting update without manual oversight.

Inspect Live Meeting Notes and Streams

Accessing meeting history with `list_notes` and `get_note` allows your OpenAI Agents SDK pipeline to extract decisions from raw text. This MCP tool reads the exact content of your meeting records to build context before executing downstream tasks. Using `list_streams` and `get_stream` lets the agent map individual notes to recurring meeting series. A clear structure ensures your automated workflows reference the correct project context every single time.

Verify Workspace Users and Connection Status

Identifying team members via `list_users` allows the OpenAI Agents SDK to assign tasks to the right person using their exact workspace email. This prevents the agent from creating orphaned tasks or assigning work to non-existent users. Running `check_fellow_status` first in your system initialization ensures the API is reachable before starting long-running agent loops. A quick status check saves execution costs by failing fast if the workspace is offline.

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 library and instantiate the streamable HTTP server class with your Vinkius endpoint. Pass this server instance in the `mcp_servers` list when initializing your Agent, allowing auto-discovery of tools like `list_meetings`.

Yes, the agent uses `list_users` to find the target email address and then calls `create_action_item` to assign the task. This flow runs through your SDK's guardrails to prevent unauthorized assignments.

Enable `cacheToolsList` in your OpenAI Agents SDK configuration to avoid redundant schema requests. This keeps tool discovery fast and saves your rate limits for actual data calls like `get_note`.

Yes, you can set up one agent to read agendas using `list_meetings` and hand off to a second agent that updates tasks via `complete_action_item`. The OpenAI Agents SDK handles these agent handoffs natively.

Your workspace emails and note contents remain inside the ephemeral Vinkius V8 sandbox during execution. No raw data is stored on Vinkius servers, as the endpoint acts as a secure, zero-trust pass-through directly to the Fellow API.

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