How to Use the Intercom MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent safely reply to Intercom conversations?

Yes, by using the replytoconversation tool. You should wrap this tool inside OpenAI's execution guardrails to inspect the generated text before it gets posted to the customer.

Q: How does the OpenAI Agents SDK handle agent handoffs for complex Intercom issues?

When your agent detects a complex issue, it uses listadmins via the MCP Server to find available staff. The agent then stops executing and routes the conversation ID to a human queue.

Q: Can the agent search for existing users before creating new ones?

It checks contacts first. The agent uses searchcontacts with specific filters to see if the user exists, and only calls createcontact if no records return.

Deploy production-grade support agents using the OpenAI Agents SDK to talk directly to your Intercom workspace with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Intercom MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe ticket deflection with the OpenAI Agents SDK

The `reply_to_conversation` tool lets your production agents answer customer tickets instantly using this MCP Server. By coupling this with OpenAI's built-in guardrails, your agent checks response safety before hitting send on live chats. To avoid hallucinating answers, the agent uses `list_help_articles` to pull verified documentation. If a customer asks something outside the docs, the agent hands off the thread to a human specialist.

Context-aware customer routing

The `get_contact_details` tool exposes customer details directly to your decision-making agents. The agent runs this lookup to verify a user's plan tier and lifetime value before deciding how to handle their request. High-value accounts get routed differently. The agent calls `list_segments` and `list_admins` to find the exact account manager assigned to that customer, ensuring VIPs never talk to a generic queue.

Automated lead enrichment

The `create_contact` tool registers new users in your workspace via the MCP endpoint the moment they interact with your application. Your agent listens to user actions and updates their profile details in real-time. To keep your data clean, the agent runs `list_data_attributes` to match custom fields. It then updates those specific attributes, preventing duplicate entries and keeping your sales pipeline accurate.

Setup guide

Set up Intercom 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 Intercom tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK, then initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this instance inside the mcp_servers list when instantiating your Agent and set cacheToolsList to True.

Yes, by using the reply_to_conversation tool. You should wrap this tool inside OpenAI's execution guardrails to inspect the generated text before it gets posted to the customer.

When your agent detects a complex issue, it uses list_admins via the MCP Server to find available staff. The agent then stops executing and routes the conversation ID to a human queue.

It checks contacts first. The agent uses search_contacts with specific filters to see if the user exists, and only calls create_contact if no records return.

Vinkius runs the server in an isolated V8 sandbox, ensuring your conversation logs and contact details are never stored. All requests to read get_conversation_details pass through ephemeral, zero-trust endpoints directly to Intercom.

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