How to Use the NeverBounce MCP in OpenAI Agents SDK

Q: How do I pass the NeverBounce MCP tools to the OpenAI Agents SDK?

You'll want the MCPServerStreamableHttp class. Pass the Vinkius endpoint URL and hand it to the Agent constructor via the mcpservers array. Tools auto-discover immediately.

Q: Can the OpenAI Agents SDK automatically check my NeverBounce credit balance?

Yes. The agent calls the getaccountinfo tool. You can write a guardrail that alerts your team when the balance gets too low.

Q: Do I need to manually define the tool schemas?

No manual configuration is required. Setting cacheToolsList=True pulls all ten tool definitions from the server once and caches them for better performance.

Auto-discover the NeverBounce MCP Server in your OpenAI Agents SDK pipelines with zero configuration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NeverBounce MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time validation for OpenAI Agents

`check_email` lets your agent instantly verify a single address before sending outbound messages. You'll integrate this directly into your handoff logic, ensuring lead-generation agents only pass valid contacts to downstream outreach agents. The built-in tracing on the dashboard captures every API call. If a validation fails, the framework guardrails catch it instantly. This prevents bounced emails from ruining your domain reputation before a campaign even starts.

Manage bulk verification autonomously

`create_job_from_url` hands your agent the ability to pull a massive CSV of contacts and submit them for processing. It works perfectly with async Python patterns. Your application continues handling other requests while the verification happens in the background. Once running, the agent checks progress using `get_job_status` and pulls the final clean list via `get_job_results`. You define the safety constraints in your code. The system handles the polling without blocking the main event loop.

Full account control via MCP Server

`get_account_info` exposes your remaining NeverBounce credits directly to the agent. This stops your production system from failing mid-run because of empty balances. You can set a rule to pause operations if credits drop below a specific threshold. You can clean up old data using `delete_job`. Reviewing past runs happens through `list_jobs`. Everything operates through the standard MCP connection, keeping your API keys securely inside the Vinkius sandbox.

Setup guide

Set up NeverBounce 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 NeverBounce tools at runtime.
3

Create your Agent

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

Run the agent

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

You'll want the `MCPServerStreamableHttp` class. Pass the Vinkius endpoint URL and hand it to the `Agent` constructor via the `mcp_servers` array. Tools auto-discover immediately.

Yes. The agent calls the `get_account_info` tool. You can write a guardrail that alerts your team when the balance gets too low.

No manual configuration is required. Setting `cacheToolsList=True` pulls all ten tool definitions from the server once and caches them for better performance.

The system catches the error through the built-in tracing. You view the exact failure reason on your dashboard and trigger a retry logic block.

The Vinkius sandbox acts as a zero-trust proxy. Your raw email addresses and CSV URLs pass through an ephemeral V8 isolate directly to the verification endpoint. We store zero contact data on our infrastructure.

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