How to Use the Hunter MCP in OpenAI Agents SDK

Q: How does Hunter handle credit usage with OpenAI Agents SDK?

You can program your agent to call emailcount before pulling a full list. This lets you check the size of a domain's email pool so you don't burn through your API quota on massive, untargeted lists.

Connect your OpenAI Agents SDK to Hunter to find, verify, and clean lead lists directly inside your production agent loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hunter MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Hunter MCP Server checks domain emails instantly

The `domain_search` tool identifies all public email addresses associated with a target company domain. Your agent runs this lookup first to map out an organization's structure and gauge the volume of available contacts before writing a single outbound message. Using `email_count` alongside this tool lets you verify how many addresses exist before spending API credits on a massive pull. This keeps your system from wasting resources on dead domains.

Target and verify contacts safely

The `email_finder` tool extracts the exact professional email address of a specific person using their name and company domain. Instead of guessing formats, your agent uses real-time data to pinpoint decision-makers instantly. To protect your domain reputation, the agent immediately feeds that result into `email_verifier` to confirm deliverability. This step stops bad data from ruining your sender score.

Track outreach lists inside OpenAI Agents SDK

The `list_leads` tool retrieves your saved prospects and campaign targets directly into your python runtimes. This lets your agent pull existing lead lists, parse their details, and prepare personalized context for upcoming campaigns. Your agent can also query `list_recipients` to see who already received an email. It prevents embarrassing double-contacts and keeps your outreach coordinated.

Setup guide

Set up Hunter 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 Hunter tools at runtime.
3

Create your Agent

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

Run the agent

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

You install the agent SDK and use the streamable HTTP server class to point to your Vinkius MCP endpoint. Pass the server instance into your agent's constructor. The agent automatically discovers all ten tools with zero manual configuration.

Yes, by combining search and verification tools. Your agent can run `email_verifier` on every found contact before sending an email. This keeps your bounce rate near zero and protects your domain.

You can program your agent to call `email_count` before pulling a full list. This lets you check the size of a domain's email pool so you don't burn through your API quota on massive, untargeted lists.

Your agent can inspect the confidence score returned by the finder tool. You can set a strict threshold in your Python code, telling the MCP client to discard any address that doesn't pass a 90% confidence check.

Your API keys and queried email addresses are handled inside a secure, ephemeral Vinkius sandbox. No email queries, domain lookups, or lead records are stored permanently on our servers. Everything runs in memory and gets destroyed immediately after the execution finishes.

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