How to Use the Lemlist MCP in OpenAI Agents SDK

Q: Can I set up guardrails for Lemlist actions in OpenAI Agents SDK?

Yes. You can intercept tool calls like deletelead or resumelead before execution inside your agent definition. This prevents the model from accidentally wiping out active campaigns or contacting blacklisted domains.

Run safe, automated cold email campaigns using OpenAI Agents SDK to control your Lemlist leads with 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 Lemlist MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate outbound steps with OpenAI Agents SDK

Let your agent manage sequences without risking your domain reputation by using `get_campaign` and `add_lead` to verify prospects. By hooking this MCP Server to your runtime, the agent checks campaign status and registers new prospects only when they meet your exact criteria. You get full visibility into every tool call on your OpenAI dashboard. The SDK handles the heavy lifting by auto-discovering these tools. If an agent tries to run a sequence on a paused campaign, your custom guardrails block the action before it hits Lemlist, keeping your outreach clean.

Coordinate multi-agent lead handoffs

Split the labor between specialized agents using `list_leads` instead of relying on one massive prompt. One agent monitors lead replies while a separate, specialized closer agent decides when to trigger `pause_lead` to stop automated follow-ups. These agent handoffs happen instantly inside the OpenAI Agents SDK runtime. Passing context between the researcher and the execution agent ensures you never send a generic cold email to a warm lead who just booked a call.

Keep campaigns moving with automated resumes

Stop babysitting your outboxes when leads go quiet by triggering `resume_lead` to kick off the next sequence phase. Your agent can scan inactive contacts and run the tool the second a prospect matches your reactivation rules. Using the MCP connection, the agent polls your team status via `get_team` to balance sending loads across multiple sender profiles. It keeps your daily volume steady without manual spreadsheet imports.

Setup guide

Set up Lemlist 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 Lemlist tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and pass the Vinkius HTTP endpoint to the streamable HTTP constructor. Your agent auto-discovers MCP tools like `add_lead` and `list_campaigns` instantly, letting you run campaigns without writing manual API wrappers.

Yes. You can intercept tool calls like `delete_lead` or `resume_lead` before execution inside your agent definition. This prevents the model from accidentally wiping out active campaigns or contacting blacklisted domains.

The OpenAI Agents SDK captures the error from the MCP Server and passes it back to the agent's context. If `add_lead` fails due to a missing email, the agent can fix the payload or log the bad record for review.

Setting the tool cache option to true prevents the SDK from repeatedly querying the server schema. This speeds up reaction times when your agent needs to quickly call `pause_lead` on a hot prospect.

Your Lemlist API keys, lead email addresses, and campaign structures never touch persistent storage. Vinkius runs the integration in isolated V8 sandboxes that self-destruct after execution, keeping your prospect lists safe from leaks.

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