How to Use the Reply.io MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK automatically pause a Reply.io sequence?

Yes, your agent can call pauseperson based on incoming email sentiment or direct user feedback. The OpenAI Agents SDK guardrails ensure the tool is only executed with valid email addresses and campaign IDs.

Q: How does the OpenAI Agents SDK handle Reply.io rate limits?

When querying listpeople or listcampaigns, the SDK respects standard backoff protocols. You can set cacheToolsList=True in your server configuration to minimize schema fetching overhead and avoid hitting API thresholds.

Q: Can I route Reply.io campaign stats between different OpenAI agents?

Yes, you can use getcampaignstats to fetch raw performance metrics and pass them to a specialized analysis agent. The SDK handles agent-to-agent handoffs naturally, allowing one agent to fetch data and another to modify sequences.

Control your Reply.io campaigns using OpenAI Agents SDK with built-in guardrails and automatic tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Reply.io MCP to OpenAI Agents SDK

Create your Vinkius account to connect Reply.io to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Reply.io with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Safely pause sequences via OpenAI Agents SDK

The `pause_person` tool stops outreach sequences instantly when your agent detects a negative reply or a manual opt-out request. This MCP Server uses built-in guardrails to verify the prospect's email format before executing this action, preventing corrupted API requests. If a prospect changes their mind, the agent invokes `resume_person` to kickstart the sequence right where it stopped. You can trace these state transitions directly inside the OpenAI developer dashboard to verify your agent's decision-making logic.

Automate lead injection with multi-agent handoffs

The `add_person` tool lets your agent inject fresh leads into active sequences without manual CSV imports. A specialized research agent finds the lead, validates their profile, and hands off the data to an outreach agent that runs the `add_person` tool. Because this MCP Server integrates with your runtime, the outreach agent automatically checks active campaign parameters using `list_campaigns` to find the correct sequence ID. This prevents sending the wrong messaging to newly acquired leads.

Monitor delivery metrics using live agent tracing

The `get_campaign_stats` tool pulls real-time open, reply, and bounce rates directly into your agent's context window. Your agent uses this raw data to determine if a specific campaign is underperforming or triggering spam filters. By coupling these stats with `list_email_accounts`, the agent identifies which sending inbox needs to be throttled. Every tool call and database lookup is logged in your tracing pipeline, giving you a clear audit trail of every email configuration change.

Setup guide

Set up Reply.io 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 Reply.io tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and register the MCP server URL using the MCPServerStreamableHttp constructor. Pass this server instance inside the mcp_servers list when initializing your Agent, and the tools will auto-discover instantly.

Yes, your agent can call pause_person based on incoming email sentiment or direct user feedback. The OpenAI Agents SDK guardrails ensure the tool is only executed with valid email addresses and campaign IDs.

When querying list_people or list_campaigns, the SDK respects standard backoff protocols. You can set cacheToolsList=True in your server configuration to minimize schema fetching overhead and avoid hitting API thresholds.

Yes, you can use get_campaign_stats to fetch raw performance metrics and pass them to a specialized analysis agent. The SDK handles agent-to-agent handoffs naturally, allowing one agent to fetch data and another to modify sequences.

Vinkius hosts the server in a zero-trust V8 Isolate sandbox, meaning your Reply.io API keys and prospect email addresses never persist on disk. All data is processed in ephemeral memory and encrypted in transit directly to the endpoint.

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