How to Use the Nylas MCP in OpenAI Agents SDK

Q: How do I connect the Nylas MCP Server to my OpenAI Agents SDK pipeline?

Install the package with pip install openai-agents and initialize MCPServerStreamableHttp using your Vinkius endpoint. Pass the server instance directly into your Agent constructor's mcpservers list to start calling tools.

Q: Can my OpenAI Agents SDK handle high-volume email checks with Nylas?

Yes. Set cacheToolsList=True in your SDK configuration to prevent redundant schema fetches when calling listmessages or listfolders. This keeps your agent responsive even during heavy traffic spikes.

Q: How does OpenAI Agents SDK manage multi-provider calendar conflicts via Nylas?

The SDK coordinates specialized agents that use listcalendars to fetch IDs across Outlook and Google, then checks availability via listevents. If a conflict exists, the scheduling agent resolves it dynamically before calling createevent.

Let your OpenAI Agents SDK system read, send, and coordinate emails and calendar invites directly through Nylas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nylas MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded email operations via OpenAI Agents SDK

`send_message` runs safely when your OpenAI Agents SDK invokes Nylas through our secure gateway. The agent automatically discovers how to draft replies, but you retain ultimate control because the SDK's built-in guardrails validate every single outbound email payload before it ever hits the wire. If your agent gets confused while parsing threads with `list_messages`, the system catches the error before any raw code executes. This setup guarantees that your automated email responders act predictably, handling `list_drafts` without risking accidental or unapproved sends.

Multi-agent calendar coordination with Nylas MCP Server

This MCP Server exposes tools like `list_calendars` and `list_events` to a network of specialized, collaborating agents. One agent can query the user's schedule, hand off the structured data to a scheduling specialist, and let it execute `create_event` with zero friction. You can trace this entire multi-agent handoff inside your OpenAI dashboard. When a booking conflict arises, the agent resolves it by invoking `delete_event` and logging the entire decision path so you can audit the workflow later.

Structured contact syncing without configuration

`list_contacts` feeds clean, deduplicated address book records directly into your OpenAI agent's context window. Setting up this pipeline takes just a few lines of Python, instantly giving your model the ability to match incoming message senders with known customer profiles. When the agent encounters a new lead, it calls `create_contact` to update the address book across Gmail or Outlook. The SDK handles the tool schema generation automatically, which means you don't have to write custom JSON schemas for this MCP integration.

Setup guide

Set up Nylas 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 Nylas tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package with `pip install openai-agents` and initialize `MCPServerStreamableHttp` using your Vinkius endpoint. Pass the server instance directly into your Agent constructor's `mcp_servers` list to start calling tools.

Yes. Set `cacheToolsList=True` in your SDK configuration to prevent redundant schema fetches when calling `list_messages` or `list_folders`. This keeps your agent responsive even during heavy traffic spikes.

The SDK coordinates specialized agents that use `list_calendars` to fetch IDs across Outlook and Google, then checks availability via `list_events`. If a conflict exists, the scheduling agent resolves it dynamically before calling `create_event`.

Initialize the HTTP transport pointing to your Vinkius URL, then let your agent call `list_drafts` to inspect pending mail. You can inspect the exact tool parameters inside your OpenAI tracing dashboard to verify how the model structures its queries.

Vinkius runs the server inside a zero-trust, ephemeral V8 Isolate sandbox that never stores your mail bodies or calendar events. Your credentials never touch the client code directly, keeping your communication data isolated and secure.

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